Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3628 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6359. Min Range: -5.6359
Max Act: 5.6359. Min Act: -0.1700
Data Index: 4671512 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6359. Min Range: -5.6359
Max Act: 5.3547. Min Act: -0.1700
Data Index: 6363990 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6359. Min Range: -5.6359
Max Act: 5.2922. Min Act: -0.1700
Data Index: 5511983 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6359. Min Range: -5.6359
Max Act: 5.2297. Min Act: -0.1700
Data Index: 8571573 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6359. Min Range: -5.6359
Max Act: 5.2297. Min Act: -0.1700
Data Index: 487665 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6359. Min Range: -5.6359
Max Act: 5.1984. Min Act: -0.1700
Data Index: 5017306 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6359. Min Range: -5.6359
Max Act: 5.1672. Min Act: -0.1700
Data Index: 5927319 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6359. Min Range: -5.6359
Max Act: 5.1359. Min Act: -0.1700
Data Index: 2054302 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6359. Min Range: -5.6359
Max Act: 5.1672. Min Act: -0.1700
Data Index: 652752 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6359. Min Range: -5.6359
Max Act: 5.1672. Min Act: -0.1700
Data Index: 7783156 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6359. Min Range: -5.6359
Max Act: 5.1359. Min Act: -0.1700
Data Index: 270365 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6359. Min Range: -5.6359
Max Act: 5.0734. Min Act: -0.1700
Data Index: 3805378 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6359. Min Range: -5.6359
Max Act: 5.1047. Min Act: -0.1700
Data Index: 4466959 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6359. Min Range: -5.6359
Max Act: 5.1047. Min Act: -0.1700
Data Index: 5108270 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6359. Min Range: -5.6359
Max Act: 5.1047. Min Act: -0.1700
Data Index: 280254 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6359. Min Range: -5.6359
Max Act: 5.0734. Min Act: -0.1700
Data Index: 3980251 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6359. Min Range: -5.6359
Max Act: 5.0734. Min Act: -0.1700
Data Index: 5919260 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6359. Min Range: -5.6359
Max Act: 5.0734. Min Act: -0.1700
Data Index: 2916782 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6359. Min Range: -5.6359
Max Act: 5.0422. Min Act: -0.1700
Data Index: 7303740 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6359. Min Range: -5.6359
Max Act: 5.0422. Min Act: -0.1700
Data Index: 3505687 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19