Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3590 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7336. Min Range: -4.7336
Max Act: 4.7336. Min Act: -0.1700
Data Index: 6104058 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7336. Min Range: -4.7336
Max Act: 4.5461. Min Act: -0.1700
Data Index: 4779487 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7336. Min Range: -4.7336
Max Act: 4.5149. Min Act: -0.1700
Data Index: 754302 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7336. Min Range: -4.7336
Max Act: 4.4211. Min Act: -0.1700
Data Index: 754301 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7336. Min Range: -4.7336
Max Act: 4.3586. Min Act: -0.1700
Data Index: 7638088 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7336. Min Range: -4.7336
Max Act: 4.3898. Min Act: -0.1700
Data Index: 206431 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7336. Min Range: -4.7336
Max Act: 4.3586. Min Act: -0.1700
Data Index: 3274396 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7336. Min Range: -4.7336
Max Act: 4.3586. Min Act: -0.1700
Data Index: 670493 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7336. Min Range: -4.7336
Max Act: 4.3586. Min Act: -0.1700
Data Index: 2142338 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7336. Min Range: -4.7336
Max Act: 4.3273. Min Act: -0.1700
Data Index: 746851 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7336. Min Range: -4.7336
Max Act: 4.3273. Min Act: -0.1700
Data Index: 507438 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7336. Min Range: -4.7336
Max Act: 4.2961. Min Act: -0.1700
Data Index: 5537898 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7336. Min Range: -4.7336
Max Act: 4.2961. Min Act: -0.1700
Data Index: 925892 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7336. Min Range: -4.7336
Max Act: 4.2961. Min Act: -0.1700
Data Index: 7299187 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7336. Min Range: -4.7336
Max Act: 4.2648. Min Act: -0.1700
Data Index: 4661097 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7336. Min Range: -4.7336
Max Act: 4.2648. Min Act: -0.1700
Data Index: 757696 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7336. Min Range: -4.7336
Max Act: 4.2648. Min Act: -0.1700
Data Index: 925882 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7336. Min Range: -4.7336
Max Act: 4.2336. Min Act: -0.1700
Data Index: 4871888 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7336. Min Range: -4.7336
Max Act: 4.2336. Min Act: -0.1700
Data Index: 5675879 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7336. Min Range: -4.7336
Max Act: 4.2336. Min Act: -0.1700
Data Index: 2084059 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19