Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1011 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3013. Min Range: -4.3013
Max Act: 4.3013. Min Act: -0.1700
Data Index: 3306285 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3013. Min Range: -4.3013
Max Act: 4.1451. Min Act: -0.1700
Data Index: 4273419 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3013. Min Range: -4.3013
Max Act: 4.1451. Min Act: -0.1700
Data Index: 31270 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3013. Min Range: -4.3013
Max Act: 4.1138. Min Act: -0.1700
Data Index: 2370566 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3013. Min Range: -4.3013
Max Act: 4.0826. Min Act: -0.1700
Data Index: 4018987 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3013. Min Range: -4.3013
Max Act: 4.0513. Min Act: -0.1700
Data Index: 4409324 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3013. Min Range: -4.3013
Max Act: 3.9888. Min Act: -0.1700
Data Index: 3799418 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3013. Min Range: -4.3013
Max Act: 3.9888. Min Act: -0.1700
Data Index: 1335737 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3013. Min Range: -4.3013
Max Act: 3.9888. Min Act: -0.1700
Data Index: 1363761 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3013. Min Range: -4.3013
Max Act: 3.9888. Min Act: -0.1700
Data Index: 5756358 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3013. Min Range: -4.3013
Max Act: 3.9888. Min Act: -0.1700
Data Index: 7433673 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3013. Min Range: -4.3013
Max Act: 3.9575. Min Act: -0.1700
Data Index: 6622525 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3013. Min Range: -4.3013
Max Act: 3.9575. Min Act: -0.1700
Data Index: 4485912 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3013. Min Range: -4.3013
Max Act: 3.9575. Min Act: -0.1700
Data Index: 1100410 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3013. Min Range: -4.3013
Max Act: 3.9575. Min Act: -0.1700
Data Index: 1660354 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3013. Min Range: -4.3013
Max Act: 3.9575. Min Act: -0.1700
Data Index: 622715 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3013. Min Range: -4.3013
Max Act: 3.9263. Min Act: -0.1700
Data Index: 1295694 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3013. Min Range: -4.3013
Max Act: 3.9263. Min Act: -0.1700
Data Index: 2777050 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3013. Min Range: -4.3013
Max Act: 3.9575. Min Act: -0.1700
Data Index: 6669770 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3013. Min Range: -4.3013
Max Act: 3.9263. Min Act: -0.1700
Data Index: 3402009 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #19