Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5831 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2370. Min Range: -6.2370
Max Act: 6.2370. Min Act: -0.1700
Data Index: 3302282 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2370. Min Range: -6.2370
Max Act: 6.2057. Min Act: -0.1700
Data Index: 6991005 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2370. Min Range: -6.2370
Max Act: 6.1432. Min Act: -0.1700
Data Index: 1340792 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2370. Min Range: -6.2370
Max Act: 6.1432. Min Act: -0.1700
Data Index: 2555676 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2370. Min Range: -6.2370
Max Act: 6.1120. Min Act: -0.1700
Data Index: 6727747 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2370. Min Range: -6.2370
Max Act: 6.1120. Min Act: -0.1700
Data Index: 6892783 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2370. Min Range: -6.2370
Max Act: 6.0807. Min Act: -0.1700
Data Index: 5340607 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2370. Min Range: -6.2370
Max Act: 6.0182. Min Act: -0.1700
Data Index: 4378207 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2370. Min Range: -6.2370
Max Act: 5.9557. Min Act: -0.1700
Data Index: 170059 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2370. Min Range: -6.2370
Max Act: 5.9557. Min Act: -0.1700
Data Index: 1912037 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2370. Min Range: -6.2370
Max Act: 5.8932. Min Act: -0.1700
Data Index: 8774059 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2370. Min Range: -6.2370
Max Act: 5.8307. Min Act: -0.1700
Data Index: 7180857 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2370. Min Range: -6.2370
Max Act: 5.8307. Min Act: -0.1700
Data Index: 8292073 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2370. Min Range: -6.2370
Max Act: 5.7682. Min Act: -0.1700
Data Index: 6100212 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2370. Min Range: -6.2370
Max Act: 5.7682. Min Act: -0.1700
Data Index: 1250076 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2370. Min Range: -6.2370
Max Act: 5.7682. Min Act: -0.1700
Data Index: 7413408 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2370. Min Range: -6.2370
Max Act: 5.7682. Min Act: -0.1700
Data Index: 6564348 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2370. Min Range: -6.2370
Max Act: 5.7682. Min Act: -0.1700
Data Index: 6305757 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2370. Min Range: -6.2370
Max Act: 5.7370. Min Act: -0.1700
Data Index: 2047601 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2370. Min Range: -6.2370
Max Act: 5.7370. Min Act: -0.1700
Data Index: 2916251 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #19