Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 50 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 8.8183. Min Range: -8.8183
Max Act: 8.8183. Min Act: -0.1700
Data Index: 456214 (C4 (Web Text))
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8183. Min Range: -8.8183
Max Act: 8.6308. Min Act: -0.1700
Data Index: 258402 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8183. Min Range: -8.8183
Max Act: 8.6933. Min Act: -0.1700
Data Index: 730181 (C4 (Web Text))
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8183. Min Range: -8.8183
Max Act: 8.6308. Min Act: -0.1700
Data Index: 1134137 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8183. Min Range: -8.8183
Max Act: 8.6308. Min Act: -0.1700
Data Index: 1170889 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8183. Min Range: -8.8183
Max Act: 8.5058. Min Act: -0.1700
Data Index: 1272129 (C4 (Web Text))
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8183. Min Range: -8.8183
Max Act: 8.6308. Min Act: -0.1700
Data Index: 646996 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8183. Min Range: -8.8183
Max Act: 8.5683. Min Act: -0.1700
Data Index: 1107281 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8183. Min Range: -8.8183
Max Act: 8.4433. Min Act: -0.1700
Data Index: 1015078 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8183. Min Range: -8.8183
Max Act: 8.4433. Min Act: -0.1700
Data Index: 517625 (C4 (Web Text))
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8183. Min Range: -8.8183
Max Act: 8.1308. Min Act: -0.1700
Data Index: 556336 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8183. Min Range: -8.8183
Max Act: 8.7558. Min Act: -0.1700
Data Index: 169567 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8183. Min Range: -8.8183
Max Act: 8.5058. Min Act: -0.1700
Data Index: 662519 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8183. Min Range: -8.8183
Max Act: 8.4433. Min Act: -0.1700
Data Index: 1350477 (C4 (Web Text))
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8183. Min Range: -8.8183
Max Act: 8.3808. Min Act: -0.1700
Data Index: 1270498 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8183. Min Range: -8.8183
Max Act: 8.5683. Min Act: -0.1700
Data Index: 188683 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8183. Min Range: -8.8183
Max Act: 8.4433. Min Act: -0.1700
Data Index: 780380 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8183. Min Range: -8.8183
Max Act: 8.5058. Min Act: -0.1700
Data Index: 183522 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8183. Min Range: -8.8183
Max Act: 8.5683. Min Act: -0.1700
Data Index: 394551 (C4 (Web Text))
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8183. Min Range: -8.8183
Max Act: 8.1620. Min Act: -0.1700
Data Index: 161324 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19