Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1021 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.6178. Min Range: -9.6178
Max Act: 9.6178. Min Act: -0.1700
Data Index: 3389946 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6178. Min Range: -9.6178
Max Act: 9.3053. Min Act: -0.1700
Data Index: 7242291 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6178. Min Range: -9.6178
Max Act: 9.2428. Min Act: -0.1700
Data Index: 4898491 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6178. Min Range: -9.6178
Max Act: 9.1178. Min Act: -0.1700
Data Index: 8406996 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6178. Min Range: -9.6178
Max Act: 9.0553. Min Act: -0.1700
Data Index: 7061600 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6178. Min Range: -9.6178
Max Act: 8.9928. Min Act: -0.1700
Data Index: 6853379 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6178. Min Range: -9.6178
Max Act: 8.8678. Min Act: -0.1700
Data Index: 4829995 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6178. Min Range: -9.6178
Max Act: 8.9303. Min Act: -0.1700
Data Index: 368156 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6178. Min Range: -9.6178
Max Act: 8.8678. Min Act: -0.1700
Data Index: 4410992 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6178. Min Range: -9.6178
Max Act: 8.9303. Min Act: -0.1700
Data Index: 4593716 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6178. Min Range: -9.6178
Max Act: 8.9303. Min Act: -0.1700
Data Index: 915417 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6178. Min Range: -9.6178
Max Act: 8.8678. Min Act: -0.1700
Data Index: 1571877 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6178. Min Range: -9.6178
Max Act: 8.9928. Min Act: -0.1700
Data Index: 640442 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6178. Min Range: -9.6178
Max Act: 8.8053. Min Act: -0.1700
Data Index: 5243743 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6178. Min Range: -9.6178
Max Act: 8.9303. Min Act: -0.1700
Data Index: 8369273 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6178. Min Range: -9.6178
Max Act: 8.8678. Min Act: -0.1700
Data Index: 8188176 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6178. Min Range: -9.6178
Max Act: 8.8678. Min Act: -0.1700
Data Index: 7846312 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6178. Min Range: -9.6178
Max Act: 8.8053. Min Act: -0.1700
Data Index: 564309 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6178. Min Range: -9.6178
Max Act: 8.8053. Min Act: -0.1700
Data Index: 1374084 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6178. Min Range: -9.6178
Max Act: 8.8053. Min Act: -0.1700
Data Index: 5039627 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #19