Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1460 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2430. Min Range: -8.2430
Max Act: 8.2117. Min Act: -0.1700
Data Index: 5610337 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2430. Min Range: -8.2430
Max Act: 8.2430. Min Act: -0.1700
Data Index: 3757103 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2430. Min Range: -8.2430
Max Act: 8.1492. Min Act: -0.1700
Data Index: 6250812 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2430. Min Range: -8.2430
Max Act: 8.2117. Min Act: -0.1700
Data Index: 201822 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2430. Min Range: -8.2430
Max Act: 8.1805. Min Act: -0.1700
Data Index: 4803126 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2430. Min Range: -8.2430
Max Act: 8.2117. Min Act: -0.1700
Data Index: 1543297 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2430. Min Range: -8.2430
Max Act: 8.1805. Min Act: -0.1700
Data Index: 6248226 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2430. Min Range: -8.2430
Max Act: 8.1805. Min Act: -0.1700
Data Index: 2754612 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2430. Min Range: -8.2430
Max Act: 8.1492. Min Act: -0.1700
Data Index: 5342 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2430. Min Range: -8.2430
Max Act: 8.1492. Min Act: -0.1700
Data Index: 8128314 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2430. Min Range: -8.2430
Max Act: 8.1180. Min Act: -0.1700
Data Index: 918697 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2430. Min Range: -8.2430
Max Act: 8.1180. Min Act: -0.1700
Data Index: 7369959 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2430. Min Range: -8.2430
Max Act: 8.1180. Min Act: -0.1700
Data Index: 3512010 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2430. Min Range: -8.2430
Max Act: 8.1492. Min Act: -0.1700
Data Index: 8583503 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2430. Min Range: -8.2430
Max Act: 8.1180. Min Act: -0.1700
Data Index: 6876546 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2430. Min Range: -8.2430
Max Act: 8.1492. Min Act: -0.1700
Data Index: 7444213 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2430. Min Range: -8.2430
Max Act: 8.1492. Min Act: -0.1700
Data Index: 8635149 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2430. Min Range: -8.2430
Max Act: 8.0867. Min Act: -0.1700
Data Index: 533406 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2430. Min Range: -8.2430
Max Act: 8.1180. Min Act: -0.1700
Data Index: 3460915 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2430. Min Range: -8.2430
Max Act: 8.0867. Min Act: -0.1700
Data Index: 5668298 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19