Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3094 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.7935. Min Act: -0.1700
Data Index: 4140888 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.6998. Min Act: -0.1700
Data Index: 1867912 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.6998. Min Act: -0.1700
Data Index: 673307 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.6998. Min Act: -0.1700
Data Index: 6318042 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.6373. Min Act: -0.1700
Data Index: 1646697 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.6685. Min Act: -0.1700
Data Index: 2685147 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.6373. Min Act: -0.1700
Data Index: 442708 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.6060. Min Act: -0.1700
Data Index: 442707 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.6373. Min Act: -0.1700
Data Index: 6048526 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.5748. Min Act: -0.1700
Data Index: 1104814 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.5435. Min Act: -0.1700
Data Index: 4206645 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.5435. Min Act: -0.1700
Data Index: 7147160 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.5123. Min Act: -0.1700
Data Index: 7147161 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.5123. Min Act: -0.1700
Data Index: 6124086 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.5123. Min Act: -0.1700
Data Index: 8605122 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.4810. Min Act: -0.1700
Data Index: 3574523 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.4810. Min Act: -0.1700
Data Index: 3384937 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.4810. Min Act: -0.1700
Data Index: 6465290 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.4810. Min Act: -0.1700
Data Index: 1836676 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.4810. Min Act: -0.1700
Data Index: 1424316 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #19