Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1107 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1349. Min Range: -5.1349
Max Act: 5.1349. Min Act: -0.1700
Data Index: 8793345 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1349. Min Range: -5.1349
Max Act: 5.1349. Min Act: -0.1700
Data Index: 8121882 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1349. Min Range: -5.1349
Max Act: 5.1036. Min Act: -0.1700
Data Index: 6361223 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1349. Min Range: -5.1349
Max Act: 5.1349. Min Act: -0.1700
Data Index: 6436738 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1349. Min Range: -5.1349
Max Act: 5.0724. Min Act: -0.1700
Data Index: 306449 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1349. Min Range: -5.1349
Max Act: 5.0724. Min Act: -0.1700
Data Index: 7579784 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1349. Min Range: -5.1349
Max Act: 5.0411. Min Act: -0.1700
Data Index: 1161640 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1349. Min Range: -5.1349
Max Act: 5.0099. Min Act: -0.1700
Data Index: 5627267 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1349. Min Range: -5.1349
Max Act: 5.0099. Min Act: -0.1700
Data Index: 6829769 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1349. Min Range: -5.1349
Max Act: 4.9786. Min Act: -0.1700
Data Index: 1757460 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1349. Min Range: -5.1349
Max Act: 5.0099. Min Act: -0.1700
Data Index: 5038635 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1349. Min Range: -5.1349
Max Act: 4.9161. Min Act: -0.1700
Data Index: 39379 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1349. Min Range: -5.1349
Max Act: 4.9474. Min Act: -0.1700
Data Index: 1923414 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1349. Min Range: -5.1349
Max Act: 4.9474. Min Act: -0.1700
Data Index: 7902621 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1349. Min Range: -5.1349
Max Act: 4.9161. Min Act: -0.1700
Data Index: 6829932 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1349. Min Range: -5.1349
Max Act: 4.9161. Min Act: -0.1700
Data Index: 8751033 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1349. Min Range: -5.1349
Max Act: 4.9161. Min Act: -0.1700
Data Index: 2158230 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1349. Min Range: -5.1349
Max Act: 4.8849. Min Act: -0.1700
Data Index: 6401348 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1349. Min Range: -5.1349
Max Act: 4.8849. Min Act: -0.1700
Data Index: 2990180 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1349. Min Range: -5.1349
Max Act: 4.8849. Min Act: -0.1700
Data Index: 4999901 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #19