Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3919 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.3112. Min Range: -9.3112
Max Act: 9.3112. Min Act: -0.1700
Data Index: 1393611 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3112. Min Range: -9.3112
Max Act: 8.9987. Min Act: -0.1700
Data Index: 1393641 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3112. Min Range: -9.3112
Max Act: 8.7487. Min Act: -0.1700
Data Index: 749832 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3112. Min Range: -9.3112
Max Act: 8.6237. Min Act: -0.1700
Data Index: 7818216 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3112. Min Range: -9.3112
Max Act: 8.6237. Min Act: -0.1700
Data Index: 1654153 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3112. Min Range: -9.3112
Max Act: 8.5612. Min Act: -0.1700
Data Index: 7332226 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3112. Min Range: -9.3112
Max Act: 8.5612. Min Act: -0.1700
Data Index: 1213454 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3112. Min Range: -9.3112
Max Act: 8.5612. Min Act: -0.1700
Data Index: 1587781 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3112. Min Range: -9.3112
Max Act: 8.5612. Min Act: -0.1700
Data Index: 7400168 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3112. Min Range: -9.3112
Max Act: 8.3737. Min Act: -0.1697
Data Index: 7818231 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3112. Min Range: -9.3112
Max Act: 8.4987. Min Act: -0.1700
Data Index: 1213457 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3112. Min Range: -9.3112
Max Act: 8.1862. Min Act: -0.1700
Data Index: 3110317 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3112. Min Range: -9.3112
Max Act: 8.0612. Min Act: -0.1700
Data Index: 8184786 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3112. Min Range: -9.3112
Max Act: 8.1237. Min Act: -0.1700
Data Index: 749833 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3112. Min Range: -9.3112
Max Act: 8.0925. Min Act: -0.1700
Data Index: 3033499 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3112. Min Range: -9.3112
Max Act: 8.1550. Min Act: -0.1700
Data Index: 587605 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3112. Min Range: -9.3112
Max Act: 8.0300. Min Act: -0.1700
Data Index: 8342240 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3112. Min Range: -9.3112
Max Act: 8.0612. Min Act: -0.1700
Data Index: 3125896 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3112. Min Range: -9.3112
Max Act: 8.0300. Min Act: -0.1700
Data Index: 4029695 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3112. Min Range: -9.3112
Max Act: 7.9050. Min Act: -0.1700
Data Index: 1242566 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19