Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4019 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9323. Min Range: -4.9323
Max Act: 4.9323. Min Act: -0.1700
Data Index: 4178405 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9323. Min Range: -4.9323
Max Act: 4.8698. Min Act: -0.1700
Data Index: 448093 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9323. Min Range: -4.9323
Max Act: 4.8698. Min Act: -0.1700
Data Index: 5009000 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9323. Min Range: -4.9323
Max Act: 4.7761. Min Act: -0.1700
Data Index: 4439382 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9323. Min Range: -4.9323
Max Act: 4.7448. Min Act: -0.1700
Data Index: 3906882 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9323. Min Range: -4.9323
Max Act: 4.7448. Min Act: -0.1700
Data Index: 3650363 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9323. Min Range: -4.9323
Max Act: 4.7448. Min Act: -0.1700
Data Index: 113582 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9323. Min Range: -4.9323
Max Act: 4.7136. Min Act: -0.1700
Data Index: 1633663 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9323. Min Range: -4.9323
Max Act: 4.7136. Min Act: -0.1700
Data Index: 880762 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9323. Min Range: -4.9323
Max Act: 4.7136. Min Act: -0.1700
Data Index: 1932756 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9323. Min Range: -4.9323
Max Act: 4.6823. Min Act: -0.1700
Data Index: 5797848 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9323. Min Range: -4.9323
Max Act: 4.6511. Min Act: -0.1700
Data Index: 7778074 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9323. Min Range: -4.9323
Max Act: 4.6511. Min Act: -0.1700
Data Index: 2634499 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9323. Min Range: -4.9323
Max Act: 4.6511. Min Act: -0.1700
Data Index: 3774228 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9323. Min Range: -4.9323
Max Act: 4.5573. Min Act: -0.1700
Data Index: 356632 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9323. Min Range: -4.9323
Max Act: 4.5886. Min Act: -0.1700
Data Index: 8675563 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9323. Min Range: -4.9323
Max Act: 4.6198. Min Act: -0.1700
Data Index: 835924 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9323. Min Range: -4.9323
Max Act: 4.5573. Min Act: -0.1700
Data Index: 1068997 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9323. Min Range: -4.9323
Max Act: 4.5573. Min Act: -0.1700
Data Index: 8119201 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9323. Min Range: -4.9323
Max Act: 4.5573. Min Act: -0.1700
Data Index: 7380332 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #19