Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3538 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.3175. Min Range: -8.3175
Max Act: 8.3175. Min Act: -0.1700
Data Index: 5654150 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3175. Min Range: -8.3175
Max Act: 8.3175. Min Act: -0.1700
Data Index: 17856 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3175. Min Range: -8.3175
Max Act: 8.2550. Min Act: -0.1700
Data Index: 2396926 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3175. Min Range: -8.3175
Max Act: 8.2550. Min Act: -0.1700
Data Index: 2248580 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3175. Min Range: -8.3175
Max Act: 8.2550. Min Act: -0.1700
Data Index: 5790714 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3175. Min Range: -8.3175
Max Act: 8.2550. Min Act: -0.1700
Data Index: 137401 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3175. Min Range: -8.3175
Max Act: 8.1925. Min Act: -0.1700
Data Index: 6568811 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3175. Min Range: -8.3175
Max Act: 8.1300. Min Act: -0.1700
Data Index: 1938138 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3175. Min Range: -8.3175
Max Act: 8.0675. Min Act: -0.1700
Data Index: 6144076 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3175. Min Range: -8.3175
Max Act: 8.0675. Min Act: -0.1700
Data Index: 4661674 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3175. Min Range: -8.3175
Max Act: 8.0050. Min Act: -0.1700
Data Index: 201360 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3175. Min Range: -8.3175
Max Act: 7.9425. Min Act: -0.1700
Data Index: 4891254 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3175. Min Range: -8.3175
Max Act: 8.0050. Min Act: -0.1700
Data Index: 1008484 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3175. Min Range: -8.3175
Max Act: 7.9425. Min Act: -0.1700
Data Index: 1674038 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3175. Min Range: -8.3175
Max Act: 7.9425. Min Act: -0.1700
Data Index: 5050861 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3175. Min Range: -8.3175
Max Act: 7.8800. Min Act: -0.1700
Data Index: 1293423 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3175. Min Range: -8.3175
Max Act: 7.8800. Min Act: -0.1700
Data Index: 3385952 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3175. Min Range: -8.3175
Max Act: 7.9425. Min Act: -0.1700
Data Index: 3004513 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3175. Min Range: -8.3175
Max Act: 8.0050. Min Act: -0.1700
Data Index: 2500547 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3175. Min Range: -8.3175
Max Act: 7.8175. Min Act: -0.1700
Data Index: 740355 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19