Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2656 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1198. Min Range: -7.1198
Max Act: 7.1198. Min Act: -0.1700
Data Index: 4089128 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1198. Min Range: -7.1198
Max Act: 7.1198. Min Act: -0.1700
Data Index: 53940 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1198. Min Range: -7.1198
Max Act: 7.0573. Min Act: -0.1700
Data Index: 3907347 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1198. Min Range: -7.1198
Max Act: 7.0573. Min Act: -0.1700
Data Index: 7249462 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1198. Min Range: -7.1198
Max Act: 7.0260. Min Act: -0.1700
Data Index: 7187153 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1198. Min Range: -7.1198
Max Act: 6.9635. Min Act: -0.1700
Data Index: 7187154 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1198. Min Range: -7.1198
Max Act: 6.9635. Min Act: -0.1700
Data Index: 2001108 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1198. Min Range: -7.1198
Max Act: 6.9323. Min Act: -0.1700
Data Index: 4107621 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1198. Min Range: -7.1198
Max Act: 6.9010. Min Act: -0.1700
Data Index: 4756119 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1198. Min Range: -7.1198
Max Act: 6.9010. Min Act: -0.1700
Data Index: 2652214 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1198. Min Range: -7.1198
Max Act: 6.8698. Min Act: -0.1700
Data Index: 2687393 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1198. Min Range: -7.1198
Max Act: 6.8698. Min Act: -0.1700
Data Index: 1730546 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1198. Min Range: -7.1198
Max Act: 6.8698. Min Act: -0.1700
Data Index: 1487419 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1198. Min Range: -7.1198
Max Act: 6.8385. Min Act: -0.1700
Data Index: 3347811 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1198. Min Range: -7.1198
Max Act: 6.8385. Min Act: -0.1700
Data Index: 7137504 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1198. Min Range: -7.1198
Max Act: 6.8073. Min Act: -0.1700
Data Index: 161091 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1198. Min Range: -7.1198
Max Act: 6.8073. Min Act: -0.1700
Data Index: 1029406 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1198. Min Range: -7.1198
Max Act: 6.8073. Min Act: -0.1700
Data Index: 5775193 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1198. Min Range: -7.1198
Max Act: 6.8073. Min Act: -0.1700
Data Index: 5492760 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1198. Min Range: -7.1198
Max Act: 6.7448. Min Act: -0.1700
Data Index: 5871110 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #19