Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6380 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2957. Min Range: -7.2957
Max Act: 7.2957. Min Act: -0.1700
Data Index: 7638504 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2957. Min Range: -7.2957
Max Act: 7.1082. Min Act: -0.1700
Data Index: 3154587 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2957. Min Range: -7.2957
Max Act: 7.1395. Min Act: -0.1700
Data Index: 4837460 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2957. Min Range: -7.2957
Max Act: 7.1395. Min Act: -0.1700
Data Index: 268957 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2957. Min Range: -7.2957
Max Act: 7.0457. Min Act: -0.1700
Data Index: 4845938 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2957. Min Range: -7.2957
Max Act: 7.0145. Min Act: -0.1700
Data Index: 5439964 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2957. Min Range: -7.2957
Max Act: 7.0145. Min Act: -0.1700
Data Index: 8742571 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2957. Min Range: -7.2957
Max Act: 6.9832. Min Act: -0.1700
Data Index: 8030310 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2957. Min Range: -7.2957
Max Act: 6.9207. Min Act: -0.1700
Data Index: 2988691 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2957. Min Range: -7.2957
Max Act: 6.9207. Min Act: -0.1700
Data Index: 6422083 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2957. Min Range: -7.2957
Max Act: 6.9207. Min Act: -0.1700
Data Index: 4215550 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2957. Min Range: -7.2957
Max Act: 6.9207. Min Act: -0.1700
Data Index: 184799 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2957. Min Range: -7.2957
Max Act: 6.8895. Min Act: -0.1700
Data Index: 1442686 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2957. Min Range: -7.2957
Max Act: 6.8895. Min Act: -0.1700
Data Index: 4742130 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2957. Min Range: -7.2957
Max Act: 6.8582. Min Act: -0.1700
Data Index: 6511434 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2957. Min Range: -7.2957
Max Act: 6.8582. Min Act: -0.1700
Data Index: 184800 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2957. Min Range: -7.2957
Max Act: 6.7957. Min Act: -0.1700
Data Index: 7529474 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2957. Min Range: -7.2957
Max Act: 6.7957. Min Act: -0.1700
Data Index: 3264598 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2957. Min Range: -7.2957
Max Act: 6.7645. Min Act: -0.1700
Data Index: 7717985 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2957. Min Range: -7.2957
Max Act: 6.7645. Min Act: -0.1700
Data Index: 6168123 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19