Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3290 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5838. Min Range: -4.5838
Max Act: 4.5838. Min Act: -0.1700
Data Index: 1808221 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5838. Min Range: -4.5838
Max Act: 4.4900. Min Act: -0.1700
Data Index: 5318927 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5838. Min Range: -4.5838
Max Act: 4.4588. Min Act: -0.1700
Data Index: 233446 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5838. Min Range: -4.5838
Max Act: 4.4275. Min Act: -0.1700
Data Index: 6972815 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5838. Min Range: -4.5838
Max Act: 4.3963. Min Act: -0.1700
Data Index: 435427 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5838. Min Range: -4.5838
Max Act: 4.3963. Min Act: -0.1700
Data Index: 6972811 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5838. Min Range: -4.5838
Max Act: 4.3963. Min Act: -0.1700
Data Index: 7356578 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5838. Min Range: -4.5838
Max Act: 4.3650. Min Act: -0.1700
Data Index: 5019993 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5838. Min Range: -4.5838
Max Act: 4.3650. Min Act: -0.1700
Data Index: 4550592 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5838. Min Range: -4.5838
Max Act: 4.3338. Min Act: -0.1700
Data Index: 2286499 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5838. Min Range: -4.5838
Max Act: 4.3338. Min Act: -0.1700
Data Index: 3487383 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5838. Min Range: -4.5838
Max Act: 4.3338. Min Act: -0.1700
Data Index: 5701130 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5838. Min Range: -4.5838
Max Act: 4.3025. Min Act: -0.1700
Data Index: 6854873 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5838. Min Range: -4.5838
Max Act: 4.3025. Min Act: -0.1700
Data Index: 6972818 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5838. Min Range: -4.5838
Max Act: 4.2713. Min Act: -0.1700
Data Index: 3279010 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5838. Min Range: -4.5838
Max Act: 4.2400. Min Act: -0.1700
Data Index: 5701128 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5838. Min Range: -4.5838
Max Act: 4.2713. Min Act: -0.1700
Data Index: 2089546 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5838. Min Range: -4.5838
Max Act: 4.2088. Min Act: -0.1700
Data Index: 6428909 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5838. Min Range: -4.5838
Max Act: 4.1775. Min Act: -0.1700
Data Index: 7308850 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5838. Min Range: -4.5838
Max Act: 4.1775. Min Act: -0.1700
Data Index: 2483324 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19