Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3682 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7904. Min Range: -6.7904
Max Act: 6.7904. Min Act: -0.1700
Data Index: 8730683 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7904. Min Range: -6.7904
Max Act: 6.7279. Min Act: -0.1700
Data Index: 4700212 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7904. Min Range: -6.7904
Max Act: 6.6654. Min Act: -0.1700
Data Index: 382759 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7904. Min Range: -6.7904
Max Act: 6.6342. Min Act: -0.1700
Data Index: 103044 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7904. Min Range: -6.7904
Max Act: 6.6029. Min Act: -0.1700
Data Index: 3274759 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7904. Min Range: -6.7904
Max Act: 6.5717. Min Act: -0.1700
Data Index: 4009899 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7904. Min Range: -6.7904
Max Act: 6.5404. Min Act: -0.1700
Data Index: 3759404 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7904. Min Range: -6.7904
Max Act: 6.5404. Min Act: -0.1700
Data Index: 6598143 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7904. Min Range: -6.7904
Max Act: 6.5092. Min Act: -0.1700
Data Index: 5596300 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7904. Min Range: -6.7904
Max Act: 6.5092. Min Act: -0.1700
Data Index: 8591436 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7904. Min Range: -6.7904
Max Act: 6.4779. Min Act: -0.1700
Data Index: 2318525 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7904. Min Range: -6.7904
Max Act: 6.4779. Min Act: -0.1700
Data Index: 7599934 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7904. Min Range: -6.7904
Max Act: 6.4467. Min Act: -0.1700
Data Index: 1209044 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7904. Min Range: -6.7904
Max Act: 6.4154. Min Act: -0.1700
Data Index: 3353975 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7904. Min Range: -6.7904
Max Act: 6.4154. Min Act: -0.1700
Data Index: 5039720 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7904. Min Range: -6.7904
Max Act: 6.3529. Min Act: -0.1700
Data Index: 6990904 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7904. Min Range: -6.7904
Max Act: 6.3842. Min Act: -0.1700
Data Index: 467332 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7904. Min Range: -6.7904
Max Act: 6.3842. Min Act: -0.1700
Data Index: 5945294 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7904. Min Range: -6.7904
Max Act: 6.3842. Min Act: -0.1700
Data Index: 8191499 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7904. Min Range: -6.7904
Max Act: 6.3529. Min Act: -0.1700
Data Index: 7059915 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19