Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 318 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.6483. Min Range: -2.6483
Max Act: 2.6483. Min Act: -0.1700
Data Index: 519317 (C4 (Web Text))
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6483. Min Range: -2.6483
Max Act: 2.5679. Min Act: -0.1700
Data Index: 366943 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6483. Min Range: -2.6483
Max Act: 2.5679. Min Act: -0.1700
Data Index: 491019 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6483. Min Range: -2.6483
Max Act: 2.5679. Min Act: -0.1700
Data Index: 1355238 (C4 (Web Text))
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6483. Min Range: -2.6483
Max Act: 2.5679. Min Act: -0.1700
Data Index: 752298 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6483. Min Range: -2.6483
Max Act: 2.5194. Min Act: -0.1700
Data Index: 60785 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6483. Min Range: -2.6483
Max Act: 2.5356. Min Act: -0.1700
Data Index: 523441 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6483. Min Range: -2.6483
Max Act: 2.5356. Min Act: -0.1700
Data Index: 1200541 (C4 (Web Text))
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6483. Min Range: -2.6483
Max Act: 2.5356. Min Act: -0.1700
Data Index: 359597 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6483. Min Range: -2.6483
Max Act: 2.5356. Min Act: -0.1700
Data Index: 1306305 (C4 (Web Text))
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6483. Min Range: -2.6483
Max Act: 2.5032. Min Act: -0.1700
Data Index: 651022 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6483. Min Range: -2.6483
Max Act: 2.5194. Min Act: -0.1700
Data Index: 91517 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6483. Min Range: -2.6483
Max Act: 2.5032. Min Act: -0.1700
Data Index: 164711 (C4 (Web Text))
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6483. Min Range: -2.6483
Max Act: 2.5032. Min Act: -0.1700
Data Index: 119542 (C4 (Web Text))
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6483. Min Range: -2.6483
Max Act: 2.5194. Min Act: -0.1700
Data Index: 289252 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6483. Min Range: -2.6483
Max Act: 2.4708. Min Act: -0.1700
Data Index: 850430 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6483. Min Range: -2.6483
Max Act: 2.4708. Min Act: -0.1700
Data Index: 1010465 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6483. Min Range: -2.6483
Max Act: 2.4708. Min Act: -0.1700
Data Index: 433594 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6483. Min Range: -2.6483
Max Act: 2.4708. Min Act: -0.1700
Data Index: 30602 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6483. Min Range: -2.6483
Max Act: 2.4221. Min Act: -0.1700
Data Index: 1231259 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #19