Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 423 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6440. Min Range: -3.6440
Max Act: 3.6440. Min Act: -0.1700
Data Index: 5515408 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6440. Min Range: -3.6440
Max Act: 3.5814. Min Act: -0.1700
Data Index: 402888 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6440. Min Range: -3.6440
Max Act: 3.5814. Min Act: -0.1700
Data Index: 1449547 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6440. Min Range: -3.6440
Max Act: 3.5814. Min Act: -0.1700
Data Index: 600433 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6440. Min Range: -3.6440
Max Act: 3.5814. Min Act: -0.1700
Data Index: 8491963 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6440. Min Range: -3.6440
Max Act: 3.5188. Min Act: -0.1700
Data Index: 1269389 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6440. Min Range: -3.6440
Max Act: 3.5501. Min Act: -0.1700
Data Index: 3672071 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6440. Min Range: -3.6440
Max Act: 3.5501. Min Act: -0.1700
Data Index: 7254056 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6440. Min Range: -3.6440
Max Act: 3.5501. Min Act: -0.1700
Data Index: 8676282 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6440. Min Range: -3.6440
Max Act: 3.5501. Min Act: -0.1700
Data Index: 3142363 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6440. Min Range: -3.6440
Max Act: 3.5501. Min Act: -0.1700
Data Index: 4943804 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6440. Min Range: -3.6440
Max Act: 3.5501. Min Act: -0.1700
Data Index: 3138593 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6440. Min Range: -3.6440
Max Act: 3.5501. Min Act: -0.1700
Data Index: 3064763 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6440. Min Range: -3.6440
Max Act: 3.5501. Min Act: -0.1700
Data Index: 8455824 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6440. Min Range: -3.6440
Max Act: 3.5188. Min Act: -0.1700
Data Index: 7761200 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6440. Min Range: -3.6440
Max Act: 3.5188. Min Act: -0.1700
Data Index: 4804536 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6440. Min Range: -3.6440
Max Act: 3.5188. Min Act: -0.1700
Data Index: 1836662 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6440. Min Range: -3.6440
Max Act: 3.4875. Min Act: -0.1700
Data Index: 6417690 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6440. Min Range: -3.6440
Max Act: 3.4875. Min Act: -0.1700
Data Index: 7317716 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6440. Min Range: -3.6440
Max Act: 3.5188. Min Act: -0.1700
Data Index: 7742493 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19