Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 27 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.8471. Min Range: -4.8471
Max Act: 4.8158. Min Act: -0.1700
Data Index: 851947 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8471. Min Range: -4.8471
Max Act: 4.8471. Min Act: -0.1700
Data Index: 38873 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8471. Min Range: -4.8471
Max Act: 4.8158. Min Act: -0.1700
Data Index: 1353339 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8471. Min Range: -4.8471
Max Act: 4.7221. Min Act: -0.1700
Data Index: 487395 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8471. Min Range: -4.8471
Max Act: 4.7221. Min Act: -0.1700
Data Index: 154554 (C4 (Web Text))
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8471. Min Range: -4.8471
Max Act: 4.7533. Min Act: -0.1700
Data Index: 962027 (C4 (Web Text))
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8471. Min Range: -4.8471
Max Act: 4.6596. Min Act: -0.1700
Data Index: 80417 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8471. Min Range: -4.8471
Max Act: 4.7221. Min Act: -0.1700
Data Index: 237605 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8471. Min Range: -4.8471
Max Act: 4.5971. Min Act: -0.1700
Data Index: 606738 (C4 (Web Text))
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8471. Min Range: -4.8471
Max Act: 4.6283. Min Act: -0.1700
Data Index: 160114 (C4 (Web Text))
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8471. Min Range: -4.8471
Max Act: 4.6596. Min Act: -0.1700
Data Index: 991752 (C4 (Web Text))
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8471. Min Range: -4.8471
Max Act: 4.5658. Min Act: -0.1700
Data Index: 545465 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8471. Min Range: -4.8471
Max Act: 4.5658. Min Act: -0.1700
Data Index: 193609 (C4 (Web Text))
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8471. Min Range: -4.8471
Max Act: 4.5346. Min Act: -0.1700
Data Index: 1342405 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8471. Min Range: -4.8471
Max Act: 4.4721. Min Act: -0.1700
Data Index: 267976 (C4 (Web Text))
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8471. Min Range: -4.8471
Max Act: 4.5033. Min Act: -0.1700
Data Index: 245484 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8471. Min Range: -4.8471
Max Act: 4.4408. Min Act: -0.1700
Data Index: 890317 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8471. Min Range: -4.8471
Max Act: 4.4721. Min Act: -0.1700
Data Index: 99108 (C4 (Web Text))
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8471. Min Range: -4.8471
Max Act: 4.4408. Min Act: -0.1700
Data Index: 12432 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8471. Min Range: -4.8471
Max Act: 4.4408. Min Act: -0.1700
Data Index: 1211189 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19