Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2409 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9207. Min Range: -3.9207
Max Act: 3.9207. Min Act: -0.1700
Data Index: 4105464 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9207. Min Range: -3.9207
Max Act: 3.8269. Min Act: -0.1700
Data Index: 7059979 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9207. Min Range: -3.9207
Max Act: 3.7956. Min Act: -0.1700
Data Index: 2981711 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9207. Min Range: -3.9207
Max Act: 3.8112. Min Act: -0.1700
Data Index: 3047157 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9207. Min Range: -3.9207
Max Act: 3.7956. Min Act: -0.1700
Data Index: 6250981 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9207. Min Range: -3.9207
Max Act: 3.7643. Min Act: -0.1700
Data Index: 337720 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9207. Min Range: -3.9207
Max Act: 3.7331. Min Act: -0.1700
Data Index: 3854591 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9207. Min Range: -3.9207
Max Act: 3.7331. Min Act: -0.1700
Data Index: 421094 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9207. Min Range: -3.9207
Max Act: 3.7174. Min Act: -0.1700
Data Index: 8321015 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9207. Min Range: -3.9207
Max Act: 3.7174. Min Act: -0.1700
Data Index: 6519300 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9207. Min Range: -3.9207
Max Act: 3.7018. Min Act: -0.1700
Data Index: 2129495 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9207. Min Range: -3.9207
Max Act: 3.7018. Min Act: -0.1700
Data Index: 4000051 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9207. Min Range: -3.9207
Max Act: 3.6861. Min Act: -0.1700
Data Index: 1281924 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9207. Min Range: -3.9207
Max Act: 3.6861. Min Act: -0.1700
Data Index: 4019646 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9207. Min Range: -3.9207
Max Act: 3.6705. Min Act: -0.1700
Data Index: 767447 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9207. Min Range: -3.9207
Max Act: 3.6861. Min Act: -0.1700
Data Index: 432446 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9207. Min Range: -3.9207
Max Act: 3.7018. Min Act: -0.1700
Data Index: 8500688 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9207. Min Range: -3.9207
Max Act: 3.6705. Min Act: -0.1700
Data Index: 8534341 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9207. Min Range: -3.9207
Max Act: 3.6392. Min Act: -0.1700
Data Index: 1189752 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9207. Min Range: -3.9207
Max Act: 3.6548. Min Act: -0.1700
Data Index: 7659386 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #19