Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 28 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7203. Min Range: -3.7203
Max Act: 3.7203. Min Act: -0.1700
Data Index: 7835746 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7203. Min Range: -3.7203
Max Act: 3.7203. Min Act: -0.1700
Data Index: 6258423 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7203. Min Range: -3.7203
Max Act: 3.7203. Min Act: -0.1700
Data Index: 3391039 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7203. Min Range: -3.7203
Max Act: 3.6577. Min Act: -0.1700
Data Index: 128194 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7203. Min Range: -3.7203
Max Act: 3.6577. Min Act: -0.1700
Data Index: 478128 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7203. Min Range: -3.7203
Max Act: 3.6577. Min Act: -0.1700
Data Index: 4922515 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7203. Min Range: -3.7203
Max Act: 3.6421. Min Act: -0.1700
Data Index: 6754664 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7203. Min Range: -3.7203
Max Act: 3.6421. Min Act: -0.1700
Data Index: 171119 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7203. Min Range: -3.7203
Max Act: 3.6264. Min Act: -0.1700
Data Index: 3919047 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7203. Min Range: -3.7203
Max Act: 3.6108. Min Act: -0.1700
Data Index: 8688143 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7203. Min Range: -3.7203
Max Act: 3.6108. Min Act: -0.1700
Data Index: 4731292 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7203. Min Range: -3.7203
Max Act: 3.5951. Min Act: -0.1700
Data Index: 1613329 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7203. Min Range: -3.7203
Max Act: 3.5951. Min Act: -0.1700
Data Index: 4925737 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7203. Min Range: -3.7203
Max Act: 3.5951. Min Act: -0.1700
Data Index: 6713610 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7203. Min Range: -3.7203
Max Act: 3.5795. Min Act: -0.1700
Data Index: 592819 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7203. Min Range: -3.7203
Max Act: 3.5951. Min Act: -0.1700
Data Index: 2187907 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7203. Min Range: -3.7203
Max Act: 3.5638. Min Act: -0.1700
Data Index: 3197526 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7203. Min Range: -3.7203
Max Act: 3.5795. Min Act: -0.1700
Data Index: 4417017 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7203. Min Range: -3.7203
Max Act: 3.5638. Min Act: -0.1700
Data Index: 6713611 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7203. Min Range: -3.7203
Max Act: 3.5638. Min Act: -0.1700
Data Index: 3144453 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #19