Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1462 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7301. Min Range: -2.7301
Max Act: 2.7301. Min Act: -0.1700
Data Index: 885003 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7301. Min Range: -2.7301
Max Act: 2.6981. Min Act: -0.1700
Data Index: 571264 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7301. Min Range: -2.7301
Max Act: 2.6981. Min Act: -0.1700
Data Index: 1340259 (C4 (Web Text))
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7301. Min Range: -2.7301
Max Act: 2.7141. Min Act: -0.1700
Data Index: 5900 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7301. Min Range: -2.7301
Max Act: 2.7141. Min Act: -0.1700
Data Index: 283917 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7301. Min Range: -2.7301
Max Act: 2.7141. Min Act: -0.1700
Data Index: 397198 (C4 (Web Text))
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7301. Min Range: -2.7301
Max Act: 2.7141. Min Act: -0.1700
Data Index: 619299 (C4 (Web Text))
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7301. Min Range: -2.7301
Max Act: 2.7141. Min Act: -0.1700
Data Index: 991111 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7301. Min Range: -2.7301
Max Act: 2.6981. Min Act: -0.1700
Data Index: 608833 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7301. Min Range: -2.7301
Max Act: 2.6981. Min Act: -0.1700
Data Index: 924416 (C4 (Web Text))
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7301. Min Range: -2.7301
Max Act: 2.6821. Min Act: -0.1700
Data Index: 633369 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7301. Min Range: -2.7301
Max Act: 2.7141. Min Act: -0.1700
Data Index: 778661 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7301. Min Range: -2.7301
Max Act: 2.6981. Min Act: -0.1700
Data Index: 1168431 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7301. Min Range: -2.7301
Max Act: 2.6821. Min Act: -0.1700
Data Index: 232744 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7301. Min Range: -2.7301
Max Act: 2.6981. Min Act: -0.1700
Data Index: 961865 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7301. Min Range: -2.7301
Max Act: 2.6981. Min Act: -0.1700
Data Index: 139006 (C4 (Web Text))
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7301. Min Range: -2.7301
Max Act: 2.6821. Min Act: -0.1700
Data Index: 1020348 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7301. Min Range: -2.7301
Max Act: 2.6821. Min Act: -0.1700
Data Index: 442318 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7301. Min Range: -2.7301
Max Act: 2.6821. Min Act: -0.1700
Data Index: 1111899 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7301. Min Range: -2.7301
Max Act: 2.6981. Min Act: -0.1700
Data Index: 708320 (C4 (Web Text))
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19