Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3089 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7476. Min Range: -5.7476
Max Act: 5.7476. Min Act: -0.1700
Data Index: 4044233 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7476. Min Range: -5.7476
Max Act: 5.1851. Min Act: -0.1700
Data Index: 3725281 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7476. Min Range: -5.7476
Max Act: 5.1226. Min Act: -0.1700
Data Index: 8594125 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7476. Min Range: -5.7476
Max Act: 5.0913. Min Act: -0.1700
Data Index: 7593660 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7476. Min Range: -5.7476
Max Act: 5.0601. Min Act: -0.1700
Data Index: 316729 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7476. Min Range: -5.7476
Max Act: 5.0913. Min Act: -0.1700
Data Index: 2250020 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7476. Min Range: -5.7476
Max Act: 5.0601. Min Act: -0.1700
Data Index: 2404335 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7476. Min Range: -5.7476
Max Act: 4.9976. Min Act: -0.1700
Data Index: 6713340 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7476. Min Range: -5.7476
Max Act: 5.0288. Min Act: -0.1700
Data Index: 7104300 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7476. Min Range: -5.7476
Max Act: 5.0288. Min Act: -0.1700
Data Index: 5477926 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7476. Min Range: -5.7476
Max Act: 5.0288. Min Act: -0.1700
Data Index: 6645917 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7476. Min Range: -5.7476
Max Act: 4.9976. Min Act: -0.1700
Data Index: 4258485 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7476. Min Range: -5.7476
Max Act: 4.9976. Min Act: -0.1700
Data Index: 1467335 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7476. Min Range: -5.7476
Max Act: 4.9976. Min Act: -0.1700
Data Index: 7982995 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7476. Min Range: -5.7476
Max Act: 4.9976. Min Act: -0.1700
Data Index: 4315835 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7476. Min Range: -5.7476
Max Act: 4.9976. Min Act: -0.1700
Data Index: 5717363 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7476. Min Range: -5.7476
Max Act: 4.9976. Min Act: -0.1700
Data Index: 5796344 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7476. Min Range: -5.7476
Max Act: 4.9976. Min Act: -0.1700
Data Index: 3988352 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7476. Min Range: -5.7476
Max Act: 4.9351. Min Act: -0.1700
Data Index: 5649983 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7476. Min Range: -5.7476
Max Act: 4.9663. Min Act: -0.1700
Data Index: 1674809 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19