Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6220 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6242. Min Range: -4.6242
Max Act: 4.6242. Min Act: -0.1700
Data Index: 5522306 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6242. Min Range: -4.6242
Max Act: 4.4992. Min Act: -0.1700
Data Index: 3710377 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6242. Min Range: -4.6242
Max Act: 4.4992. Min Act: -0.1700
Data Index: 5038727 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6242. Min Range: -4.6242
Max Act: 4.4992. Min Act: -0.1699
Data Index: 1007685 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6242. Min Range: -4.6242
Max Act: 4.4992. Min Act: -0.1700
Data Index: 7211738 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6242. Min Range: -4.6242
Max Act: 4.4679. Min Act: -0.1700
Data Index: 6085023 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6242. Min Range: -4.6242
Max Act: 4.4679. Min Act: -0.1700
Data Index: 1504745 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6242. Min Range: -4.6242
Max Act: 4.4992. Min Act: -0.1700
Data Index: 2511352 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6242. Min Range: -4.6242
Max Act: 4.4679. Min Act: -0.1700
Data Index: 2093717 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6242. Min Range: -4.6242
Max Act: 4.4679. Min Act: -0.1700
Data Index: 8622062 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6242. Min Range: -4.6242
Max Act: 4.4367. Min Act: -0.1700
Data Index: 3337748 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6242. Min Range: -4.6242
Max Act: 4.4367. Min Act: -0.1700
Data Index: 111808 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6242. Min Range: -4.6242
Max Act: 4.4367. Min Act: -0.1700
Data Index: 1967602 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6242. Min Range: -4.6242
Max Act: 4.4054. Min Act: -0.1700
Data Index: 1813443 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6242. Min Range: -4.6242
Max Act: 4.4054. Min Act: -0.1700
Data Index: 6659602 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6242. Min Range: -4.6242
Max Act: 4.4054. Min Act: -0.1700
Data Index: 4251452 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6242. Min Range: -4.6242
Max Act: 4.3742. Min Act: -0.1700
Data Index: 5814153 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6242. Min Range: -4.6242
Max Act: 4.4054. Min Act: -0.1700
Data Index: 1504752 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6242. Min Range: -4.6242
Max Act: 4.4054. Min Act: -0.1700
Data Index: 8036025 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6242. Min Range: -4.6242
Max Act: 4.3742. Min Act: -0.1700
Data Index: 1672395 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #19