Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2387 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9824. Min Range: -4.9824
Max Act: 4.9824. Min Act: -0.1700
Data Index: 8799052 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9824. Min Range: -4.9824
Max Act: 4.9511. Min Act: -0.1700
Data Index: 4506694 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9824. Min Range: -4.9824
Max Act: 4.9199. Min Act: -0.1700
Data Index: 6023794 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9824. Min Range: -4.9824
Max Act: 4.9199. Min Act: -0.1700
Data Index: 3448173 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9824. Min Range: -4.9824
Max Act: 4.9199. Min Act: -0.1700
Data Index: 1820970 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9824. Min Range: -4.9824
Max Act: 4.8886. Min Act: -0.1700
Data Index: 7220512 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9824. Min Range: -4.9824
Max Act: 4.9199. Min Act: -0.1700
Data Index: 3078013 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9824. Min Range: -4.9824
Max Act: 4.8261. Min Act: -0.1700
Data Index: 2154950 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9824. Min Range: -4.9824
Max Act: 4.8574. Min Act: -0.1700
Data Index: 3682098 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9824. Min Range: -4.9824
Max Act: 4.8574. Min Act: -0.1700
Data Index: 6098539 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9824. Min Range: -4.9824
Max Act: 4.8261. Min Act: -0.1700
Data Index: 7627078 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9824. Min Range: -4.9824
Max Act: 4.8574. Min Act: -0.1700
Data Index: 3341279 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9824. Min Range: -4.9824
Max Act: 4.8574. Min Act: -0.1700
Data Index: 6101249 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9824. Min Range: -4.9824
Max Act: 4.8261. Min Act: -0.1700
Data Index: 375 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9824. Min Range: -4.9824
Max Act: 4.8261. Min Act: -0.1700
Data Index: 2152410 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9824. Min Range: -4.9824
Max Act: 4.8261. Min Act: -0.1700
Data Index: 1119192 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9824. Min Range: -4.9824
Max Act: 4.8261. Min Act: -0.1700
Data Index: 1640209 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9824. Min Range: -4.9824
Max Act: 4.8261. Min Act: -0.1700
Data Index: 4419806 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9824. Min Range: -4.9824
Max Act: 4.7949. Min Act: -0.1700
Data Index: 6431473 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9824. Min Range: -4.9824
Max Act: 4.7949. Min Act: -0.1700
Data Index: 3655142 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19