Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 806 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8983. Min Range: -5.8983
Max Act: 5.8983. Min Act: -0.1700
Data Index: 8817395 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8983. Min Range: -5.8983
Max Act: 5.6171. Min Act: -0.1700
Data Index: 1122167 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8983. Min Range: -5.8983
Max Act: 5.6483. Min Act: -0.1700
Data Index: 1625275 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8983. Min Range: -5.8983
Max Act: 5.6171. Min Act: -0.1700
Data Index: 4117347 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8983. Min Range: -5.8983
Max Act: 5.6171. Min Act: -0.1700
Data Index: 441585 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8983. Min Range: -5.8983
Max Act: 5.5858. Min Act: -0.1700
Data Index: 3500994 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8983. Min Range: -5.8983
Max Act: 5.5858. Min Act: -0.1700
Data Index: 8402985 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8983. Min Range: -5.8983
Max Act: 5.5546. Min Act: -0.1700
Data Index: 7850251 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8983. Min Range: -5.8983
Max Act: 5.4921. Min Act: -0.1700
Data Index: 1221667 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8983. Min Range: -5.8983
Max Act: 5.4921. Min Act: -0.1700
Data Index: 7192592 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8983. Min Range: -5.8983
Max Act: 5.4608. Min Act: -0.1700
Data Index: 7059500 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8983. Min Range: -5.8983
Max Act: 5.3983. Min Act: -0.1700
Data Index: 3105974 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8983. Min Range: -5.8983
Max Act: 5.3671. Min Act: -0.1700
Data Index: 423455 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8983. Min Range: -5.8983
Max Act: 5.4296. Min Act: -0.1700
Data Index: 7448007 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8983. Min Range: -5.8983
Max Act: 5.4608. Min Act: -0.1700
Data Index: 2867413 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8983. Min Range: -5.8983
Max Act: 5.3983. Min Act: -0.1700
Data Index: 3934698 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8983. Min Range: -5.8983
Max Act: 5.3671. Min Act: -0.1700
Data Index: 6655603 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8983. Min Range: -5.8983
Max Act: 5.3983. Min Act: -0.1700
Data Index: 1742998 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8983. Min Range: -5.8983
Max Act: 5.3983. Min Act: -0.1700
Data Index: 282145 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8983. Min Range: -5.8983
Max Act: 5.3358. Min Act: -0.1700
Data Index: 5744320 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #19