Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 45 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0777. Min Range: -7.0777
Max Act: 7.0777. Min Act: -0.1700
Data Index: 7778828 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0777. Min Range: -7.0777
Max Act: 6.3590. Min Act: -0.1700
Data Index: 7778827 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0777. Min Range: -7.0777
Max Act: 6.3277. Min Act: -0.1700
Data Index: 775223 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0777. Min Range: -7.0777
Max Act: 6.2652. Min Act: -0.1700
Data Index: 7924352 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0777. Min Range: -7.0777
Max Act: 6.2027. Min Act: -0.1700
Data Index: 6612528 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0777. Min Range: -7.0777
Max Act: 6.1402. Min Act: -0.1700
Data Index: 1663506 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0777. Min Range: -7.0777
Max Act: 6.1402. Min Act: -0.1700
Data Index: 8511702 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0777. Min Range: -7.0777
Max Act: 6.1090. Min Act: -0.1700
Data Index: 6935637 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0777. Min Range: -7.0777
Max Act: 6.1090. Min Act: -0.1700
Data Index: 8702330 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0777. Min Range: -7.0777
Max Act: 6.0777. Min Act: -0.1700
Data Index: 2252298 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0777. Min Range: -7.0777
Max Act: 6.0465. Min Act: -0.1700
Data Index: 2494371 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0777. Min Range: -7.0777
Max Act: 6.0465. Min Act: -0.1700
Data Index: 8585469 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0777. Min Range: -7.0777
Max Act: 6.0152. Min Act: -0.1700
Data Index: 6836412 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0777. Min Range: -7.0777
Max Act: 5.9840. Min Act: -0.1700
Data Index: 5562415 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0777. Min Range: -7.0777
Max Act: 5.9527. Min Act: -0.1700
Data Index: 5545208 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0777. Min Range: -7.0777
Max Act: 5.9840. Min Act: -0.1700
Data Index: 1993278 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0777. Min Range: -7.0777
Max Act: 5.9215. Min Act: -0.1700
Data Index: 3918898 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0777. Min Range: -7.0777
Max Act: 5.8902. Min Act: -0.1700
Data Index: 8257989 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0777. Min Range: -7.0777
Max Act: 5.9215. Min Act: -0.1700
Data Index: 7015028 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0777. Min Range: -7.0777
Max Act: 5.9215. Min Act: -0.1700
Data Index: 2586411 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19