Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3772 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4598. Min Range: -3.4598
Max Act: 3.4598. Min Act: -0.1700
Data Index: 7584581 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4598. Min Range: -3.4598
Max Act: 3.4284. Min Act: -0.1700
Data Index: 565131 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4598. Min Range: -3.4598
Max Act: 3.3343. Min Act: -0.1700
Data Index: 8032391 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4598. Min Range: -3.4598
Max Act: 3.3186. Min Act: -0.1700
Data Index: 7850105 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4598. Min Range: -3.4598
Max Act: 3.2715. Min Act: -0.1700
Data Index: 6985997 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4598. Min Range: -3.4598
Max Act: 3.2558. Min Act: -0.1700
Data Index: 1383235 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4598. Min Range: -3.4598
Max Act: 3.2558. Min Act: -0.1700
Data Index: 8734241 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4598. Min Range: -3.4598
Max Act: 3.2558. Min Act: -0.1700
Data Index: 8292358 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4598. Min Range: -3.4598
Max Act: 3.2558. Min Act: -0.1700
Data Index: 4908028 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4598. Min Range: -3.4598
Max Act: 3.2244. Min Act: -0.1700
Data Index: 6779136 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4598. Min Range: -3.4598
Max Act: 3.2401. Min Act: -0.1700
Data Index: 3737205 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4598. Min Range: -3.4598
Max Act: 3.2087. Min Act: -0.1700
Data Index: 5554456 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4598. Min Range: -3.4598
Max Act: 3.1930. Min Act: -0.1700
Data Index: 932377 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4598. Min Range: -3.4598
Max Act: 3.1772. Min Act: -0.1700
Data Index: 4133113 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4598. Min Range: -3.4598
Max Act: 3.1772. Min Act: -0.1700
Data Index: 6250318 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4598. Min Range: -3.4598
Max Act: 3.1772. Min Act: -0.1700
Data Index: 6177076 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4598. Min Range: -3.4598
Max Act: 3.1615. Min Act: -0.1700
Data Index: 3156198 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4598. Min Range: -3.4598
Max Act: 3.1615. Min Act: -0.1700
Data Index: 6470903 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4598. Min Range: -3.4598
Max Act: 3.1615. Min Act: -0.1700
Data Index: 704960 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4598. Min Range: -3.4598
Max Act: 3.1615. Min Act: -0.1700
Data Index: 1565054 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19