Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2210 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7108. Min Range: -7.7108
Max Act: 7.7108. Min Act: -0.1700
Data Index: 4831096 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7108. Min Range: -7.7108
Max Act: 7.7108. Min Act: -0.1700
Data Index: 7221851 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7108. Min Range: -7.7108
Max Act: 7.6483. Min Act: -0.1700
Data Index: 1853729 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7108. Min Range: -7.7108
Max Act: 7.6483. Min Act: -0.1700
Data Index: 2307055 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7108. Min Range: -7.7108
Max Act: 7.6483. Min Act: -0.1700
Data Index: 1172304 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7108. Min Range: -7.7108
Max Act: 7.5858. Min Act: -0.1700
Data Index: 8685181 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7108. Min Range: -7.7108
Max Act: 7.5546. Min Act: -0.1700
Data Index: 2670864 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7108. Min Range: -7.7108
Max Act: 7.5546. Min Act: -0.1700
Data Index: 6760634 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7108. Min Range: -7.7108
Max Act: 7.5233. Min Act: -0.1700
Data Index: 4467457 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7108. Min Range: -7.7108
Max Act: 7.4921. Min Act: -0.1700
Data Index: 8203868 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7108. Min Range: -7.7108
Max Act: 7.4608. Min Act: -0.1700
Data Index: 1046942 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7108. Min Range: -7.7108
Max Act: 7.4296. Min Act: -0.1700
Data Index: 7779499 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7108. Min Range: -7.7108
Max Act: 7.3983. Min Act: -0.1700
Data Index: 1312786 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7108. Min Range: -7.7108
Max Act: 7.3983. Min Act: -0.1700
Data Index: 7769921 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7108. Min Range: -7.7108
Max Act: 7.3358. Min Act: -0.1700
Data Index: 1232709 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7108. Min Range: -7.7108
Max Act: 7.3358. Min Act: -0.1700
Data Index: 2415991 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7108. Min Range: -7.7108
Max Act: 7.3358. Min Act: -0.1700
Data Index: 6420521 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7108. Min Range: -7.7108
Max Act: 7.3358. Min Act: -0.1700
Data Index: 2703580 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7108. Min Range: -7.7108
Max Act: 7.3046. Min Act: -0.1700
Data Index: 5809028 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7108. Min Range: -7.7108
Max Act: 7.2421. Min Act: -0.1700
Data Index: 5399804 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19