Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3382 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0177. Min Range: -6.0177
Max Act: 6.0177. Min Act: -0.1700
Data Index: 2866732 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0177. Min Range: -6.0177
Max Act: 5.7989. Min Act: -0.1700
Data Index: 6430986 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0177. Min Range: -6.0177
Max Act: 5.7364. Min Act: -0.1700
Data Index: 3415281 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0177. Min Range: -6.0177
Max Act: 5.7364. Min Act: -0.1700
Data Index: 7273715 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0177. Min Range: -6.0177
Max Act: 5.7052. Min Act: -0.1700
Data Index: 3174564 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0177. Min Range: -6.0177
Max Act: 5.7052. Min Act: -0.1700
Data Index: 6323992 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0177. Min Range: -6.0177
Max Act: 5.6739. Min Act: -0.1700
Data Index: 1607051 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0177. Min Range: -6.0177
Max Act: 5.6739. Min Act: -0.1700
Data Index: 1182732 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0177. Min Range: -6.0177
Max Act: 5.6739. Min Act: -0.1700
Data Index: 2150259 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0177. Min Range: -6.0177
Max Act: 5.6427. Min Act: -0.1700
Data Index: 6086157 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0177. Min Range: -6.0177
Max Act: 5.5802. Min Act: -0.1700
Data Index: 4529169 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0177. Min Range: -6.0177
Max Act: 5.5177. Min Act: -0.1700
Data Index: 5607960 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0177. Min Range: -6.0177
Max Act: 5.4864. Min Act: -0.1700
Data Index: 7234371 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0177. Min Range: -6.0177
Max Act: 5.4864. Min Act: -0.1700
Data Index: 6839851 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0177. Min Range: -6.0177
Max Act: 5.4864. Min Act: -0.1700
Data Index: 3971735 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0177. Min Range: -6.0177
Max Act: 5.4552. Min Act: -0.1700
Data Index: 8393791 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0177. Min Range: -6.0177
Max Act: 5.4552. Min Act: -0.1700
Data Index: 6951618 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0177. Min Range: -6.0177
Max Act: 5.4239. Min Act: -0.1700
Data Index: 6194871 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0177. Min Range: -6.0177
Max Act: 5.4239. Min Act: -0.1700
Data Index: 3684080 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0177. Min Range: -6.0177
Max Act: 5.3927. Min Act: -0.1700
Data Index: 7992632 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19