Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1194 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0392. Min Range: -5.0392
Max Act: 5.0392. Min Act: -0.1700
Data Index: 118256 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0392. Min Range: -5.0392
Max Act: 5.0079. Min Act: -0.1700
Data Index: 7661328 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0392. Min Range: -5.0392
Max Act: 5.0079. Min Act: -0.1700
Data Index: 3824262 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0392. Min Range: -5.0392
Max Act: 5.0079. Min Act: -0.1700
Data Index: 5565388 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0392. Min Range: -5.0392
Max Act: 4.9767. Min Act: -0.1700
Data Index: 1463588 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0392. Min Range: -5.0392
Max Act: 4.9142. Min Act: -0.1700
Data Index: 1653345 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0392. Min Range: -5.0392
Max Act: 4.8517. Min Act: -0.1700
Data Index: 3913444 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0392. Min Range: -5.0392
Max Act: 4.8204. Min Act: -0.1700
Data Index: 7174114 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0392. Min Range: -5.0392
Max Act: 4.8204. Min Act: -0.1700
Data Index: 6744326 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0392. Min Range: -5.0392
Max Act: 4.7892. Min Act: -0.1700
Data Index: 4583463 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0392. Min Range: -5.0392
Max Act: 4.7892. Min Act: -0.1700
Data Index: 7651276 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0392. Min Range: -5.0392
Max Act: 4.7892. Min Act: -0.1700
Data Index: 3141091 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0392. Min Range: -5.0392
Max Act: 4.7892. Min Act: -0.1700
Data Index: 5278274 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0392. Min Range: -5.0392
Max Act: 4.7892. Min Act: -0.1700
Data Index: 1582398 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0392. Min Range: -5.0392
Max Act: 4.7892. Min Act: -0.1700
Data Index: 8187387 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0392. Min Range: -5.0392
Max Act: 4.7892. Min Act: -0.1700
Data Index: 5947356 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0392. Min Range: -5.0392
Max Act: 4.7579. Min Act: -0.1700
Data Index: 6235696 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0392. Min Range: -5.0392
Max Act: 4.7579. Min Act: -0.1700
Data Index: 777010 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0392. Min Range: -5.0392
Max Act: 4.7579. Min Act: -0.1700
Data Index: 1684509 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0392. Min Range: -5.0392
Max Act: 4.7579. Min Act: -0.1700
Data Index: 1902276 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19