Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2694 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6770. Min Range: -8.6770
Max Act: 8.6770. Min Act: -0.1700
Data Index: 1287600 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6770. Min Range: -8.6770
Max Act: 7.7708. Min Act: -0.1700
Data Index: 5357706 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6770. Min Range: -8.6770
Max Act: 7.6145. Min Act: -0.1700
Data Index: 8482632 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6770. Min Range: -8.6770
Max Act: 7.5520. Min Act: -0.1700
Data Index: 5402393 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6770. Min Range: -8.6770
Max Act: 7.5520. Min Act: -0.1700
Data Index: 2549455 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6770. Min Range: -8.6770
Max Act: 7.5208. Min Act: -0.1700
Data Index: 7040262 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6770. Min Range: -8.6770
Max Act: 7.4270. Min Act: -0.1700
Data Index: 5081556 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6770. Min Range: -8.6770
Max Act: 7.4583. Min Act: -0.1700
Data Index: 6710494 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6770. Min Range: -8.6770
Max Act: 7.3958. Min Act: -0.1700
Data Index: 2410668 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6770. Min Range: -8.6770
Max Act: 7.3958. Min Act: -0.1700
Data Index: 4714523 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6770. Min Range: -8.6770
Max Act: 7.3958. Min Act: -0.1700
Data Index: 3079335 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6770. Min Range: -8.6770
Max Act: 7.3645. Min Act: -0.1700
Data Index: 67734 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6770. Min Range: -8.6770
Max Act: 7.3645. Min Act: -0.1700
Data Index: 2573900 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6770. Min Range: -8.6770
Max Act: 7.3645. Min Act: -0.1700
Data Index: 8765913 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6770. Min Range: -8.6770
Max Act: 7.2708. Min Act: -0.1700
Data Index: 2797047 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6770. Min Range: -8.6770
Max Act: 7.2395. Min Act: -0.1700
Data Index: 2907721 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6770. Min Range: -8.6770
Max Act: 7.2083. Min Act: -0.1700
Data Index: 751277 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6770. Min Range: -8.6770
Max Act: 7.2395. Min Act: -0.1700
Data Index: 2792122 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6770. Min Range: -8.6770
Max Act: 7.1770. Min Act: -0.1700
Data Index: 1946021 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6770. Min Range: -8.6770
Max Act: 7.1770. Min Act: -0.1700
Data Index: 5471078 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19