Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3917 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5945. Min Range: -3.5945
Max Act: 3.5945. Min Act: -0.1700
Data Index: 2214674 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5945. Min Range: -3.5945
Max Act: 3.3438. Min Act: -0.1700
Data Index: 6912643 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5945. Min Range: -3.5945
Max Act: 3.3124. Min Act: -0.1700
Data Index: 6346940 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5945. Min Range: -3.5945
Max Act: 3.2339. Min Act: -0.1700
Data Index: 1524492 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5945. Min Range: -3.5945
Max Act: 3.2339. Min Act: -0.1700
Data Index: 1715667 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5945. Min Range: -3.5945
Max Act: 3.2339. Min Act: -0.1700
Data Index: 4034713 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5945. Min Range: -3.5945
Max Act: 3.2024. Min Act: -0.1700
Data Index: 1492564 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5945. Min Range: -3.5945
Max Act: 3.2182. Min Act: -0.1700
Data Index: 6349421 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5945. Min Range: -3.5945
Max Act: 3.1867. Min Act: -0.1700
Data Index: 1877763 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5945. Min Range: -3.5945
Max Act: 3.2024. Min Act: -0.1700
Data Index: 6397781 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5945. Min Range: -3.5945
Max Act: 3.2024. Min Act: -0.1700
Data Index: 1654897 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5945. Min Range: -3.5945
Max Act: 3.2024. Min Act: -0.1700
Data Index: 5005025 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5945. Min Range: -3.5945
Max Act: 3.2024. Min Act: -0.1700
Data Index: 6056247 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5945. Min Range: -3.5945
Max Act: 3.1867. Min Act: -0.1700
Data Index: 7395014 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5945. Min Range: -3.5945
Max Act: 3.1710. Min Act: -0.1700
Data Index: 3652525 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5945. Min Range: -3.5945
Max Act: 3.1710. Min Act: -0.1700
Data Index: 3787509 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5945. Min Range: -3.5945
Max Act: 3.1710. Min Act: -0.1700
Data Index: 3451961 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5945. Min Range: -3.5945
Max Act: 3.1395. Min Act: -0.1700
Data Index: 2091412 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5945. Min Range: -3.5945
Max Act: 3.1552. Min Act: -0.1700
Data Index: 6257495 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5945. Min Range: -3.5945
Max Act: 3.1710. Min Act: -0.1700
Data Index: 1299221 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19