Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3738 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4819. Min Range: -6.4819
Max Act: 6.4819. Min Act: -0.1700
Data Index: 3006189 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4819. Min Range: -6.4819
Max Act: 6.3881. Min Act: -0.1700
Data Index: 1088450 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4819. Min Range: -6.4819
Max Act: 6.3881. Min Act: -0.1700
Data Index: 1088445 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4819. Min Range: -6.4819
Max Act: 6.3569. Min Act: -0.1700
Data Index: 2051963 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4819. Min Range: -6.4819
Max Act: 6.2944. Min Act: -0.1700
Data Index: 7945162 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4819. Min Range: -6.4819
Max Act: 6.2944. Min Act: -0.1700
Data Index: 2292357 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4819. Min Range: -6.4819
Max Act: 6.2944. Min Act: -0.1700
Data Index: 589381 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4819. Min Range: -6.4819
Max Act: 6.2631. Min Act: -0.1700
Data Index: 3120222 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4819. Min Range: -6.4819
Max Act: 6.2006. Min Act: -0.1700
Data Index: 249694 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4819. Min Range: -6.4819
Max Act: 6.2006. Min Act: -0.1700
Data Index: 4279028 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4819. Min Range: -6.4819
Max Act: 6.1381. Min Act: -0.1700
Data Index: 1039956 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4819. Min Range: -6.4819
Max Act: 6.1694. Min Act: -0.1700
Data Index: 1778841 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4819. Min Range: -6.4819
Max Act: 6.1694. Min Act: -0.1700
Data Index: 5293831 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4819. Min Range: -6.4819
Max Act: 6.1694. Min Act: -0.1700
Data Index: 6297840 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4819. Min Range: -6.4819
Max Act: 6.1381. Min Act: -0.1700
Data Index: 4006240 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4819. Min Range: -6.4819
Max Act: 6.1381. Min Act: -0.1700
Data Index: 5764777 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4819. Min Range: -6.4819
Max Act: 6.1069. Min Act: -0.1700
Data Index: 1909261 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4819. Min Range: -6.4819
Max Act: 6.1381. Min Act: -0.1700
Data Index: 325736 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4819. Min Range: -6.4819
Max Act: 6.0756. Min Act: -0.1700
Data Index: 1757225 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4819. Min Range: -6.4819
Max Act: 6.0756. Min Act: -0.1700
Data Index: 1926680 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #19