Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 825 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7103. Min Range: -6.7103
Max Act: 6.7103. Min Act: -0.1700
Data Index: 875548 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7103. Min Range: -6.7103
Max Act: 6.6791. Min Act: -0.1700
Data Index: 3628957 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7103. Min Range: -6.7103
Max Act: 6.6166. Min Act: -0.1700
Data Index: 7344706 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7103. Min Range: -6.7103
Max Act: 6.6166. Min Act: -0.1700
Data Index: 3981736 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7103. Min Range: -6.7103
Max Act: 6.5853. Min Act: -0.1700
Data Index: 6226070 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7103. Min Range: -6.7103
Max Act: 6.5853. Min Act: -0.1700
Data Index: 4907382 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7103. Min Range: -6.7103
Max Act: 6.5228. Min Act: -0.1700
Data Index: 3359792 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7103. Min Range: -6.7103
Max Act: 6.4916. Min Act: -0.1700
Data Index: 2037562 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7103. Min Range: -6.7103
Max Act: 6.5228. Min Act: -0.1700
Data Index: 5408461 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7103. Min Range: -6.7103
Max Act: 6.4916. Min Act: -0.1700
Data Index: 4370719 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7103. Min Range: -6.7103
Max Act: 6.4603. Min Act: -0.1700
Data Index: 2869822 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7103. Min Range: -6.7103
Max Act: 6.4603. Min Act: -0.1700
Data Index: 8622709 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7103. Min Range: -6.7103
Max Act: 6.4603. Min Act: -0.1700
Data Index: 7495988 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7103. Min Range: -6.7103
Max Act: 6.4603. Min Act: -0.1700
Data Index: 3153693 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7103. Min Range: -6.7103
Max Act: 6.4291. Min Act: -0.1700
Data Index: 3504890 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7103. Min Range: -6.7103
Max Act: 6.4291. Min Act: -0.1700
Data Index: 1424406 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7103. Min Range: -6.7103
Max Act: 6.4291. Min Act: -0.1700
Data Index: 1424408 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7103. Min Range: -6.7103
Max Act: 6.3666. Min Act: -0.1700
Data Index: 1021197 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7103. Min Range: -6.7103
Max Act: 6.3666. Min Act: -0.1700
Data Index: 7180902 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7103. Min Range: -6.7103
Max Act: 6.3353. Min Act: -0.1700
Data Index: 2317530 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #19