Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2160 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8415. Min Range: -5.8415
Max Act: 5.8415. Min Act: -0.1700
Data Index: 933629 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8415. Min Range: -5.8415
Max Act: 5.8102. Min Act: -0.1700
Data Index: 6482276 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8415. Min Range: -5.8415
Max Act: 5.8102. Min Act: -0.1700
Data Index: 8234933 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8415. Min Range: -5.8415
Max Act: 5.6852. Min Act: -0.1700
Data Index: 60154 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8415. Min Range: -5.8415
Max Act: 5.6227. Min Act: -0.1700
Data Index: 3934124 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8415. Min Range: -5.8415
Max Act: 5.5915. Min Act: -0.1700
Data Index: 7721175 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8415. Min Range: -5.8415
Max Act: 5.5290. Min Act: -0.1700
Data Index: 7413269 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8415. Min Range: -5.8415
Max Act: 5.5290. Min Act: -0.1700
Data Index: 327170 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8415. Min Range: -5.8415
Max Act: 5.5602. Min Act: -0.1700
Data Index: 6784580 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8415. Min Range: -5.8415
Max Act: 5.5290. Min Act: -0.1700
Data Index: 7987961 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8415. Min Range: -5.8415
Max Act: 5.5602. Min Act: -0.1700
Data Index: 2753153 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8415. Min Range: -5.8415
Max Act: 5.5290. Min Act: -0.1700
Data Index: 1386808 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8415. Min Range: -5.8415
Max Act: 5.5290. Min Act: -0.1700
Data Index: 2773792 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8415. Min Range: -5.8415
Max Act: 5.5290. Min Act: -0.1700
Data Index: 4903528 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8415. Min Range: -5.8415
Max Act: 5.5290. Min Act: -0.1700
Data Index: 7517616 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8415. Min Range: -5.8415
Max Act: 5.4665. Min Act: -0.1700
Data Index: 3721948 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8415. Min Range: -5.8415
Max Act: 5.4977. Min Act: -0.1700
Data Index: 3928779 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8415. Min Range: -5.8415
Max Act: 5.4977. Min Act: -0.1700
Data Index: 3077089 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8415. Min Range: -5.8415
Max Act: 5.4977. Min Act: -0.1700
Data Index: 5724171 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8415. Min Range: -5.8415
Max Act: 5.4665. Min Act: -0.1700
Data Index: 2232283 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19