Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5448 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1811. Min Range: -9.1811
Max Act: 9.1811. Min Act: -0.1700
Data Index: 6046779 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1811. Min Range: -9.1811
Max Act: 8.8686. Min Act: -0.1700
Data Index: 3514032 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1811. Min Range: -9.1811
Max Act: 8.7436. Min Act: -0.1700
Data Index: 3691266 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1811. Min Range: -9.1811
Max Act: 8.7436. Min Act: -0.1700
Data Index: 3653375 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1811. Min Range: -9.1811
Max Act: 8.6811. Min Act: -0.1700
Data Index: 6046777 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1811. Min Range: -9.1811
Max Act: 8.5561. Min Act: -0.1700
Data Index: 7096784 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1811. Min Range: -9.1811
Max Act: 8.5561. Min Act: -0.1700
Data Index: 2074854 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1811. Min Range: -9.1811
Max Act: 8.5561. Min Act: -0.1700
Data Index: 2214186 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1811. Min Range: -9.1811
Max Act: 8.6186. Min Act: -0.1700
Data Index: 8806726 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1811. Min Range: -9.1811
Max Act: 8.6186. Min Act: -0.1700
Data Index: 3711192 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1811. Min Range: -9.1811
Max Act: 8.4936. Min Act: -0.1700
Data Index: 5535645 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1811. Min Range: -9.1811
Max Act: 8.4936. Min Act: -0.1700
Data Index: 7735834 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1811. Min Range: -9.1811
Max Act: 8.4936. Min Act: -0.1700
Data Index: 6212892 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1811. Min Range: -9.1811
Max Act: 8.4936. Min Act: -0.1700
Data Index: 4868687 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1811. Min Range: -9.1811
Max Act: 8.4936. Min Act: -0.1700
Data Index: 2997203 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1811. Min Range: -9.1811
Max Act: 8.4936. Min Act: -0.1700
Data Index: 5624467 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1811. Min Range: -9.1811
Max Act: 8.4311. Min Act: -0.1700
Data Index: 1272847 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1811. Min Range: -9.1811
Max Act: 8.4311. Min Act: -0.1700
Data Index: 5842307 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1811. Min Range: -9.1811
Max Act: 8.4311. Min Act: -0.1700
Data Index: 6306938 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1811. Min Range: -9.1811
Max Act: 8.3686. Min Act: -0.1700
Data Index: 6649508 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #19