Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3780 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2545. Min Range: -6.2545
Max Act: 6.2545. Min Act: -0.1700
Data Index: 6634212 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2545. Min Range: -6.2545
Max Act: 6.1608. Min Act: -0.1700
Data Index: 3061048 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2545. Min Range: -6.2545
Max Act: 6.0983. Min Act: -0.1700
Data Index: 4684781 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2545. Min Range: -6.2545
Max Act: 6.1295. Min Act: -0.1700
Data Index: 8019246 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2545. Min Range: -6.2545
Max Act: 6.1295. Min Act: -0.1700
Data Index: 5245957 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2545. Min Range: -6.2545
Max Act: 6.0983. Min Act: -0.1700
Data Index: 3396500 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2545. Min Range: -6.2545
Max Act: 6.0983. Min Act: -0.1700
Data Index: 4184668 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2545. Min Range: -6.2545
Max Act: 6.0670. Min Act: -0.1700
Data Index: 6113782 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2545. Min Range: -6.2545
Max Act: 6.0670. Min Act: -0.1700
Data Index: 6615617 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2545. Min Range: -6.2545
Max Act: 6.0670. Min Act: -0.1700
Data Index: 6079167 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2545. Min Range: -6.2545
Max Act: 6.0670. Min Act: -0.1700
Data Index: 5287035 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2545. Min Range: -6.2545
Max Act: 6.0670. Min Act: -0.1700
Data Index: 3791561 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2545. Min Range: -6.2545
Max Act: 6.0670. Min Act: -0.1700
Data Index: 4010474 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2545. Min Range: -6.2545
Max Act: 6.0670. Min Act: -0.1700
Data Index: 7629814 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2545. Min Range: -6.2545
Max Act: 6.0358. Min Act: -0.1700
Data Index: 1762135 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2545. Min Range: -6.2545
Max Act: 6.0358. Min Act: -0.1700
Data Index: 979356 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2545. Min Range: -6.2545
Max Act: 6.0358. Min Act: -0.1700
Data Index: 6385901 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2545. Min Range: -6.2545
Max Act: 6.0045. Min Act: -0.1700
Data Index: 6460940 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2545. Min Range: -6.2545
Max Act: 6.0358. Min Act: -0.1700
Data Index: 7002996 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2545. Min Range: -6.2545
Max Act: 6.0358. Min Act: -0.1700
Data Index: 4710476 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19