Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1536 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.1653. Min Range: -7.1653
Max Act: 7.1653. Min Act: -0.1700
Data Index: 463365 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1653. Min Range: -7.1653
Max Act: 7.0716. Min Act: -0.1700
Data Index: 2026160 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1653. Min Range: -7.1653
Max Act: 7.0091. Min Act: -0.1700
Data Index: 6058732 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1653. Min Range: -7.1653
Max Act: 7.0403. Min Act: -0.1700
Data Index: 938347 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1653. Min Range: -7.1653
Max Act: 6.9466. Min Act: -0.1700
Data Index: 6217903 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1653. Min Range: -7.1653
Max Act: 6.9153. Min Act: -0.1700
Data Index: 7096091 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1653. Min Range: -7.1653
Max Act: 6.8528. Min Act: -0.1700
Data Index: 8650500 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1653. Min Range: -7.1653
Max Act: 6.7591. Min Act: -0.1700
Data Index: 5658068 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1653. Min Range: -7.1653
Max Act: 6.7903. Min Act: -0.1700
Data Index: 2000275 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1653. Min Range: -7.1653
Max Act: 6.8216. Min Act: -0.1700
Data Index: 4677629 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1653. Min Range: -7.1653
Max Act: 6.7591. Min Act: -0.1700
Data Index: 3268309 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1653. Min Range: -7.1653
Max Act: 6.7278. Min Act: -0.1700
Data Index: 6610927 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1653. Min Range: -7.1653
Max Act: 6.7591. Min Act: -0.1700
Data Index: 6453214 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1653. Min Range: -7.1653
Max Act: 6.7278. Min Act: -0.1700
Data Index: 4223717 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1653. Min Range: -7.1653
Max Act: 6.7278. Min Act: -0.1700
Data Index: 8401505 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1653. Min Range: -7.1653
Max Act: 6.7591. Min Act: -0.1700
Data Index: 5555872 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1653. Min Range: -7.1653
Max Act: 6.7278. Min Act: -0.1700
Data Index: 680078 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1653. Min Range: -7.1653
Max Act: 6.6966. Min Act: -0.1700
Data Index: 914206 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1653. Min Range: -7.1653
Max Act: 6.6653. Min Act: -0.1700
Data Index: 1862222 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1653. Min Range: -7.1653
Max Act: 6.6653. Min Act: -0.1700
Data Index: 6193028 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #19