Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3033 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3226. Min Range: -5.3226
Max Act: 5.3226. Min Act: -0.1700
Data Index: 2545260 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3226. Min Range: -5.3226
Max Act: 5.3226. Min Act: -0.1700
Data Index: 3685843 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3226. Min Range: -5.3226
Max Act: 5.2601. Min Act: -0.1700
Data Index: 6216722 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3226. Min Range: -5.3226
Max Act: 5.2289. Min Act: -0.1700
Data Index: 7729010 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3226. Min Range: -5.3226
Max Act: 5.1664. Min Act: -0.1700
Data Index: 7968088 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3226. Min Range: -5.3226
Max Act: 5.1351. Min Act: -0.1700
Data Index: 7386691 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3226. Min Range: -5.3226
Max Act: 5.1039. Min Act: -0.1700
Data Index: 7254669 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3226. Min Range: -5.3226
Max Act: 5.0101. Min Act: -0.1700
Data Index: 1908419 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3226. Min Range: -5.3226
Max Act: 5.0101. Min Act: -0.1700
Data Index: 7057239 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3226. Min Range: -5.3226
Max Act: 4.9476. Min Act: -0.1700
Data Index: 7456201 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3226. Min Range: -5.3226
Max Act: 4.9164. Min Act: -0.1700
Data Index: 4198671 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3226. Min Range: -5.3226
Max Act: 4.9476. Min Act: -0.1700
Data Index: 96854 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3226. Min Range: -5.3226
Max Act: 4.9164. Min Act: -0.1700
Data Index: 4228927 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3226. Min Range: -5.3226
Max Act: 4.8539. Min Act: -0.1700
Data Index: 3372971 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3226. Min Range: -5.3226
Max Act: 4.8539. Min Act: -0.1700
Data Index: 668185 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3226. Min Range: -5.3226
Max Act: 4.7914. Min Act: -0.1700
Data Index: 8433939 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3226. Min Range: -5.3226
Max Act: 4.8226. Min Act: -0.1700
Data Index: 8309608 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3226. Min Range: -5.3226
Max Act: 4.7914. Min Act: -0.1700
Data Index: 2762588 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3226. Min Range: -5.3226
Max Act: 4.7914. Min Act: -0.1700
Data Index: 1665263 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3226. Min Range: -5.3226
Max Act: 4.7289. Min Act: -0.1700
Data Index: 2710746 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #19