Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2746 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3466. Min Range: -6.3466
Max Act: 6.3466. Min Act: -0.1700
Data Index: 2204117 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3466. Min Range: -6.3466
Max Act: 6.1591. Min Act: -0.1700
Data Index: 1859948 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3466. Min Range: -6.3466
Max Act: 6.1279. Min Act: -0.1700
Data Index: 1969507 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3466. Min Range: -6.3466
Max Act: 6.0654. Min Act: -0.1700
Data Index: 6101279 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3466. Min Range: -6.3466
Max Act: 6.0341. Min Act: -0.1700
Data Index: 4927876 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3466. Min Range: -6.3466
Max Act: 5.9404. Min Act: -0.1700
Data Index: 6633675 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3466. Min Range: -6.3466
Max Act: 5.9716. Min Act: -0.1700
Data Index: 1859950 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3466. Min Range: -6.3466
Max Act: 5.9404. Min Act: -0.1700
Data Index: 7242689 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3466. Min Range: -6.3466
Max Act: 5.9091. Min Act: -0.1700
Data Index: 3414743 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3466. Min Range: -6.3466
Max Act: 5.9091. Min Act: -0.1700
Data Index: 4959782 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3466. Min Range: -6.3466
Max Act: 5.9091. Min Act: -0.1700
Data Index: 5505214 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3466. Min Range: -6.3466
Max Act: 5.9091. Min Act: -0.1700
Data Index: 38753 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3466. Min Range: -6.3466
Max Act: 5.8154. Min Act: -0.1700
Data Index: 5234451 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3466. Min Range: -6.3466
Max Act: 5.8154. Min Act: -0.1700
Data Index: 5992628 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3466. Min Range: -6.3466
Max Act: 5.8154. Min Act: -0.1700
Data Index: 3627043 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3466. Min Range: -6.3466
Max Act: 5.7529. Min Act: -0.1700
Data Index: 3385407 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3466. Min Range: -6.3466
Max Act: 5.7841. Min Act: -0.1700
Data Index: 6285076 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3466. Min Range: -6.3466
Max Act: 5.7841. Min Act: -0.1700
Data Index: 5404862 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3466. Min Range: -6.3466
Max Act: 5.7841. Min Act: -0.1700
Data Index: 6121898 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3466. Min Range: -6.3466
Max Act: 5.7529. Min Act: -0.1700
Data Index: 767463 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #19