Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1733 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.1247. Min Range: -4.1247
Max Act: 4.1247. Min Act: -0.1700
Data Index: 451857 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1247. Min Range: -4.1247
Max Act: 4.0309. Min Act: -0.1700
Data Index: 662251 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1247. Min Range: -4.1247
Max Act: 3.9371. Min Act: -0.1700
Data Index: 1150372 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1247. Min Range: -4.1247
Max Act: 3.9684. Min Act: -0.1700
Data Index: 960626 (C4 (Web Text))
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1247. Min Range: -4.1247
Max Act: 3.9371. Min Act: -0.1700
Data Index: 658216 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1247. Min Range: -4.1247
Max Act: 3.9371. Min Act: -0.1700
Data Index: 604192 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1247. Min Range: -4.1247
Max Act: 3.9371. Min Act: -0.1700
Data Index: 513067 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1247. Min Range: -4.1247
Max Act: 3.9059. Min Act: -0.1700
Data Index: 649781 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1247. Min Range: -4.1247
Max Act: 3.8746. Min Act: -0.1700
Data Index: 248428 (C4 (Web Text))
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1247. Min Range: -4.1247
Max Act: 3.9059. Min Act: -0.1700
Data Index: 1224536 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1247. Min Range: -4.1247
Max Act: 3.8433. Min Act: -0.1700
Data Index: 395104 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1247. Min Range: -4.1247
Max Act: 3.8433. Min Act: -0.1700
Data Index: 156185 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1247. Min Range: -4.1247
Max Act: 3.8746. Min Act: -0.1700
Data Index: 1330529 (C4 (Web Text))
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1247. Min Range: -4.1247
Max Act: 3.8746. Min Act: -0.1700
Data Index: 143872 (C4 (Web Text))
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1247. Min Range: -4.1247
Max Act: 3.8433. Min Act: -0.1700
Data Index: 908351 (C4 (Web Text))
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1247. Min Range: -4.1247
Max Act: 3.8433. Min Act: -0.1700
Data Index: 538668 (C4 (Web Text))
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1247. Min Range: -4.1247
Max Act: 3.8746. Min Act: -0.1700
Data Index: 721399 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1247. Min Range: -4.1247
Max Act: 3.8120. Min Act: -0.1700
Data Index: 730343 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1247. Min Range: -4.1247
Max Act: 3.8120. Min Act: -0.1700
Data Index: 269043 (C4 (Web Text))
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1247. Min Range: -4.1247
Max Act: 3.8433. Min Act: -0.1700
Data Index: 1168538 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #19