Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 507 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.3650. Min Range: -2.3650
Max Act: 2.3486. Min Act: -0.1700
Data Index: 927283 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3650. Min Range: -2.3650
Max Act: 2.3650. Min Act: -0.1700
Data Index: 884197 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3650. Min Range: -2.3650
Max Act: 2.3322. Min Act: -0.1700
Data Index: 197672 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3650. Min Range: -2.3650
Max Act: 2.2994. Min Act: -0.1700
Data Index: 794098 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3650. Min Range: -2.3650
Max Act: 2.2829. Min Act: -0.1700
Data Index: 1477203 (Python Code)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3650. Min Range: -2.3650
Max Act: 2.2829. Min Act: -0.1700
Data Index: 494637 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3650. Min Range: -2.3650
Max Act: 2.2829. Min Act: -0.1700
Data Index: 1184932 (C4 (Web Text))
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3650. Min Range: -2.3650
Max Act: 2.2829. Min Act: -0.1700
Data Index: 1286788 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3650. Min Range: -2.3650
Max Act: 2.2829. Min Act: -0.1700
Data Index: 1061932 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3650. Min Range: -2.3650
Max Act: 2.2829. Min Act: -0.1700
Data Index: 1144511 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3650. Min Range: -2.3650
Max Act: 2.2665. Min Act: -0.1700
Data Index: 1111702 (C4 (Web Text))
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3650. Min Range: -2.3650
Max Act: 2.2500. Min Act: -0.1700
Data Index: 208099 (C4 (Web Text))
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3650. Min Range: -2.3650
Max Act: 2.2665. Min Act: -0.1700
Data Index: 219246 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3650. Min Range: -2.3650
Max Act: 2.2665. Min Act: -0.1700
Data Index: 145393 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3650. Min Range: -2.3650
Max Act: 2.2665. Min Act: -0.1700
Data Index: 328183 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3650. Min Range: -2.3650
Max Act: 2.2500. Min Act: -0.1700
Data Index: 866013 (C4 (Web Text))
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3650. Min Range: -2.3650
Max Act: 2.2500. Min Act: -0.1700
Data Index: 775406 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3650. Min Range: -2.3650
Max Act: 2.2665. Min Act: -0.1700
Data Index: 1204013 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3650. Min Range: -2.3650
Max Act: 2.2334. Min Act: -0.1700
Data Index: 805249 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3650. Min Range: -2.3650
Max Act: 2.2500. Min Act: -0.1700
Data Index: 54374 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19