Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5904 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.1605. Min Range: -1.1605
Max Act: 1.1605. Min Act: -0.1700
Data Index: 4927906 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1605. Min Range: -1.1605
Max Act: 1.1254. Min Act: -0.1700
Data Index: 159905 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1605. Min Range: -1.1605
Max Act: 1.0903. Min Act: -0.1699
Data Index: 6699325 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1605. Min Range: -1.1605
Max Act: 1.0728. Min Act: -0.1700
Data Index: 8518866 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1605. Min Range: -1.1605
Max Act: 1.0728. Min Act: -0.1700
Data Index: 6696948 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1605. Min Range: -1.1605
Max Act: 1.0903. Min Act: -0.1700
Data Index: 5871040 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1605. Min Range: -1.1605
Max Act: 1.0553. Min Act: -0.1700
Data Index: 6173447 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1605. Min Range: -1.1605
Max Act: 1.0379. Min Act: -0.1700
Data Index: 5317525 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1605. Min Range: -1.1605
Max Act: 1.0379. Min Act: -0.1700
Data Index: 3059554 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1605. Min Range: -1.1605
Max Act: 1.0379. Min Act: -0.1699
Data Index: 7667440 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1605. Min Range: -1.1605
Max Act: 1.0379. Min Act: -0.1699
Data Index: 7302848 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1605. Min Range: -1.1605
Max Act: 1.0379. Min Act: -0.1695
Data Index: 6466724 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1605. Min Range: -1.1605
Max Act: 1.0379. Min Act: -0.1700
Data Index: 7233155 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1605. Min Range: -1.1605
Max Act: 1.0379. Min Act: -0.1700
Data Index: 8518871 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1605. Min Range: -1.1605
Max Act: 1.0379. Min Act: -0.1700
Data Index: 7794929 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1605. Min Range: -1.1605
Max Act: 1.0205. Min Act: -0.1700
Data Index: 7167749 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1605. Min Range: -1.1605
Max Act: 1.0205. Min Act: -0.1700
Data Index: 4398925 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1605. Min Range: -1.1605
Max Act: 1.0205. Min Act: -0.1700
Data Index: 4350143 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1605. Min Range: -1.1605
Max Act: 1.0205. Min Act: -0.1700
Data Index: 1355970 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1605. Min Range: -1.1605
Max Act: 0.9944. Min Act: -0.1700
Data Index: 2042518 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #19