Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3697 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6342. Min Range: -5.6342
Max Act: 5.6342. Min Act: -0.1700
Data Index: 674786 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6342. Min Range: -5.6342
Max Act: 5.5092. Min Act: -0.1700
Data Index: 4646116 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6342. Min Range: -5.6342
Max Act: 5.4155. Min Act: -0.1700
Data Index: 7212899 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6342. Min Range: -5.6342
Max Act: 5.3842. Min Act: -0.1700
Data Index: 2527198 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6342. Min Range: -5.6342
Max Act: 5.3842. Min Act: -0.1700
Data Index: 6883859 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6342. Min Range: -5.6342
Max Act: 5.3530. Min Act: -0.1700
Data Index: 7581013 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6342. Min Range: -5.6342
Max Act: 5.3217. Min Act: -0.1700
Data Index: 1905056 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6342. Min Range: -5.6342
Max Act: 5.2905. Min Act: -0.1700
Data Index: 5126446 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6342. Min Range: -5.6342
Max Act: 5.2592. Min Act: -0.1700
Data Index: 3701535 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6342. Min Range: -5.6342
Max Act: 5.2905. Min Act: -0.1700
Data Index: 2706741 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6342. Min Range: -5.6342
Max Act: 5.2280. Min Act: -0.1700
Data Index: 7804868 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6342. Min Range: -5.6342
Max Act: 5.2592. Min Act: -0.1700
Data Index: 4319840 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6342. Min Range: -5.6342
Max Act: 5.2592. Min Act: -0.1700
Data Index: 3098369 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6342. Min Range: -5.6342
Max Act: 5.1655. Min Act: -0.1700
Data Index: 3056297 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6342. Min Range: -5.6342
Max Act: 5.1655. Min Act: -0.1700
Data Index: 3713435 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6342. Min Range: -5.6342
Max Act: 5.1655. Min Act: -0.1700
Data Index: 5788738 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6342. Min Range: -5.6342
Max Act: 5.1342. Min Act: -0.1700
Data Index: 8009042 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6342. Min Range: -5.6342
Max Act: 5.1342. Min Act: -0.1700
Data Index: 1887659 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6342. Min Range: -5.6342
Max Act: 5.1342. Min Act: -0.1700
Data Index: 1394524 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6342. Min Range: -5.6342
Max Act: 5.1342. Min Act: -0.1700
Data Index: 6194531 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19