Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3597 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0419. Min Range: -5.0419
Max Act: 5.0419. Min Act: -0.1700
Data Index: 7197372 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0419. Min Range: -5.0419
Max Act: 4.9481. Min Act: -0.1700
Data Index: 1934914 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0419. Min Range: -5.0419
Max Act: 4.9481. Min Act: -0.1700
Data Index: 1992148 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0419. Min Range: -5.0419
Max Act: 4.9169. Min Act: -0.1700
Data Index: 4707967 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0419. Min Range: -5.0419
Max Act: 4.8856. Min Act: -0.1700
Data Index: 6297317 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0419. Min Range: -5.0419
Max Act: 4.8856. Min Act: -0.1700
Data Index: 7197374 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0419. Min Range: -5.0419
Max Act: 4.8544. Min Act: -0.1700
Data Index: 2812735 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0419. Min Range: -5.0419
Max Act: 4.8231. Min Act: -0.1700
Data Index: 1992147 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0419. Min Range: -5.0419
Max Act: 4.8544. Min Act: -0.1700
Data Index: 4865871 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0419. Min Range: -5.0419
Max Act: 4.8231. Min Act: -0.1700
Data Index: 3267728 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0419. Min Range: -5.0419
Max Act: 4.8231. Min Act: -0.1700
Data Index: 7175796 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0419. Min Range: -5.0419
Max Act: 4.8231. Min Act: -0.1700
Data Index: 4865869 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0419. Min Range: -5.0419
Max Act: 4.7919. Min Act: -0.1700
Data Index: 1937211 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0419. Min Range: -5.0419
Max Act: 4.8231. Min Act: -0.1700
Data Index: 7197368 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0419. Min Range: -5.0419
Max Act: 4.8544. Min Act: -0.1700
Data Index: 2009118 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0419. Min Range: -5.0419
Max Act: 4.7919. Min Act: -0.1700
Data Index: 457246 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0419. Min Range: -5.0419
Max Act: 4.7919. Min Act: -0.1700
Data Index: 4707966 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0419. Min Range: -5.0419
Max Act: 4.7919. Min Act: -0.1700
Data Index: 6297315 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0419. Min Range: -5.0419
Max Act: 4.7919. Min Act: -0.1700
Data Index: 381233 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0419. Min Range: -5.0419
Max Act: 4.7919. Min Act: -0.1700
Data Index: 233433 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19