Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3548 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9084. Min Range: -10.9084
Max Act: 10.9084. Min Act: -0.1700
Data Index: 8437979 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9084. Min Range: -10.9084
Max Act: 10.7834. Min Act: -0.1700
Data Index: 3454849 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9084. Min Range: -10.9084
Max Act: 10.7209. Min Act: -0.1692
Data Index: 3874355 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9084. Min Range: -10.9084
Max Act: 10.7209. Min Act: -0.1700
Data Index: 4826162 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9084. Min Range: -10.9084
Max Act: 10.7209. Min Act: -0.1699
Data Index: 5753693 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9084. Min Range: -10.9084
Max Act: 10.6584. Min Act: -0.1700
Data Index: 8115603 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9084. Min Range: -10.9084
Max Act: 10.5334. Min Act: -0.1700
Data Index: 5347700 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9084. Min Range: -10.9084
Max Act: 10.5334. Min Act: -0.1700
Data Index: 7676190 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9084. Min Range: -10.9084
Max Act: 10.5334. Min Act: -0.1700
Data Index: 2511933 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9084. Min Range: -10.9084
Max Act: 10.4709. Min Act: -0.1700
Data Index: 5364355 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9084. Min Range: -10.9084
Max Act: 10.4709. Min Act: -0.1700
Data Index: 7119713 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9084. Min Range: -10.9084
Max Act: 10.4084. Min Act: -0.1698
Data Index: 1338319 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9084. Min Range: -10.9084
Max Act: 10.4084. Min Act: -0.1700
Data Index: 4355330 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9084. Min Range: -10.9084
Max Act: 10.3459. Min Act: -0.1700
Data Index: 5547134 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9084. Min Range: -10.9084
Max Act: 10.3459. Min Act: -0.1700
Data Index: 1944186 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9084. Min Range: -10.9084
Max Act: 10.4084. Min Act: -0.1699
Data Index: 1914149 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9084. Min Range: -10.9084
Max Act: 10.2834. Min Act: -0.1700
Data Index: 7426966 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9084. Min Range: -10.9084
Max Act: 10.2834. Min Act: -0.1700
Data Index: 8643336 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9084. Min Range: -10.9084
Max Act: 10.2834. Min Act: -0.1700
Data Index: 5409883 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9084. Min Range: -10.9084
Max Act: 10.1584. Min Act: -0.1700
Data Index: 6134094 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19