Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 20 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.3216. Min Range: -4.3216
Max Act: 4.3216. Min Act: -0.1700
Data Index: 1356496 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3216. Min Range: -4.3216
Max Act: 4.2903. Min Act: -0.1700
Data Index: 944330 (C4 (Web Text))
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3216. Min Range: -4.3216
Max Act: 4.1966. Min Act: -0.1700
Data Index: 205874 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3216. Min Range: -4.3216
Max Act: 4.2278. Min Act: -0.1700
Data Index: 588267 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3216. Min Range: -4.3216
Max Act: 4.2278. Min Act: -0.1700
Data Index: 912352 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3216. Min Range: -4.3216
Max Act: 4.2591. Min Act: -0.1700
Data Index: 794417 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3216. Min Range: -4.3216
Max Act: 4.1966. Min Act: -0.1700
Data Index: 585452 (C4 (Web Text))
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3216. Min Range: -4.3216
Max Act: 4.1653. Min Act: -0.1700
Data Index: 241070 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3216. Min Range: -4.3216
Max Act: 4.1966. Min Act: -0.1700
Data Index: 146439 (C4 (Web Text))
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3216. Min Range: -4.3216
Max Act: 4.1653. Min Act: -0.1700
Data Index: 1158607 (C4 (Web Text))
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3216. Min Range: -4.3216
Max Act: 4.1653. Min Act: -0.1700
Data Index: 1029046 (C4 (Web Text))
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3216. Min Range: -4.3216
Max Act: 4.1341. Min Act: -0.1700
Data Index: 288393 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3216. Min Range: -4.3216
Max Act: 4.1341. Min Act: -0.1700
Data Index: 303935 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3216. Min Range: -4.3216
Max Act: 4.1341. Min Act: -0.1700
Data Index: 718713 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3216. Min Range: -4.3216
Max Act: 4.1341. Min Act: -0.1700
Data Index: 910114 (C4 (Web Text))
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3216. Min Range: -4.3216
Max Act: 4.1341. Min Act: -0.1700
Data Index: 938804 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3216. Min Range: -4.3216
Max Act: 4.1341. Min Act: -0.1700
Data Index: 991874 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3216. Min Range: -4.3216
Max Act: 4.1341. Min Act: -0.1700
Data Index: 378413 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3216. Min Range: -4.3216
Max Act: 4.1341. Min Act: -0.1700
Data Index: 400604 (C4 (Web Text))
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3216. Min Range: -4.3216
Max Act: 4.1341. Min Act: -0.1700
Data Index: 1034562 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19