Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2766 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0979. Min Range: -5.0979
Max Act: 5.0979. Min Act: -0.1700
Data Index: 1429081 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0979. Min Range: -5.0979
Max Act: 4.9416. Min Act: -0.1700
Data Index: 684225 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0979. Min Range: -5.0979
Max Act: 4.9416. Min Act: -0.1700
Data Index: 3508232 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0979. Min Range: -5.0979
Max Act: 4.8479. Min Act: -0.1700
Data Index: 4445809 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0979. Min Range: -5.0979
Max Act: 4.8479. Min Act: -0.1700
Data Index: 716412 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0979. Min Range: -5.0979
Max Act: 4.6604. Min Act: -0.1700
Data Index: 6081918 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0979. Min Range: -5.0979
Max Act: 4.6916. Min Act: -0.1700
Data Index: 8227100 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0979. Min Range: -5.0979
Max Act: 4.6291. Min Act: -0.1700
Data Index: 4128418 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0979. Min Range: -5.0979
Max Act: 4.5666. Min Act: -0.1700
Data Index: 6275860 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0979. Min Range: -5.0979
Max Act: 4.5354. Min Act: -0.1700
Data Index: 7778245 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0979. Min Range: -5.0979
Max Act: 4.4729. Min Act: -0.1700
Data Index: 2032411 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0979. Min Range: -5.0979
Max Act: 4.5041. Min Act: -0.1700
Data Index: 5943429 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0979. Min Range: -5.0979
Max Act: 4.4729. Min Act: -0.1700
Data Index: 6483642 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0979. Min Range: -5.0979
Max Act: 4.4416. Min Act: -0.1700
Data Index: 6846534 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0979. Min Range: -5.0979
Max Act: 4.4729. Min Act: -0.1700
Data Index: 3095567 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0979. Min Range: -5.0979
Max Act: 4.4416. Min Act: -0.1700
Data Index: 4713359 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0979. Min Range: -5.0979
Max Act: 4.4104. Min Act: -0.1700
Data Index: 1132779 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0979. Min Range: -5.0979
Max Act: 4.4104. Min Act: -0.1700
Data Index: 5091086 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0979. Min Range: -5.0979
Max Act: 4.3479. Min Act: -0.1700
Data Index: 250136 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0979. Min Range: -5.0979
Max Act: 4.3791. Min Act: -0.1700
Data Index: 5207117 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19