Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 209 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7231. Min Range: -2.7231
Max Act: 2.7231. Min Act: -0.1700
Data Index: 204570 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7231. Min Range: -2.7231
Max Act: 2.6590. Min Act: -0.1700
Data Index: 997362 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7231. Min Range: -2.7231
Max Act: 2.6590. Min Act: -0.1700
Data Index: 507712 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7231. Min Range: -2.7231
Max Act: 2.5948. Min Act: -0.1700
Data Index: 376962 (C4 (Web Text))
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7231. Min Range: -2.7231
Max Act: 2.5625. Min Act: -0.1700
Data Index: 367075 (C4 (Web Text))
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7231. Min Range: -2.7231
Max Act: 2.5464. Min Act: -0.1700
Data Index: 581103 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7231. Min Range: -2.7231
Max Act: 2.5464. Min Act: -0.1700
Data Index: 690121 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7231. Min Range: -2.7231
Max Act: 2.5464. Min Act: -0.1700
Data Index: 1223046 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7231. Min Range: -2.7231
Max Act: 2.5464. Min Act: -0.1700
Data Index: 1171567 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7231. Min Range: -2.7231
Max Act: 2.5464. Min Act: -0.1700
Data Index: 943912 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7231. Min Range: -2.7231
Max Act: 2.5302. Min Act: -0.1700
Data Index: 647012 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7231. Min Range: -2.7231
Max Act: 2.5302. Min Act: -0.1700
Data Index: 498976 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7231. Min Range: -2.7231
Max Act: 2.5464. Min Act: -0.1700
Data Index: 74784 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7231. Min Range: -2.7231
Max Act: 2.5302. Min Act: -0.1700
Data Index: 629123 (C4 (Web Text))
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7231. Min Range: -2.7231
Max Act: 2.5141. Min Act: -0.1700
Data Index: 1347293 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7231. Min Range: -2.7231
Max Act: 2.5141. Min Act: -0.1700
Data Index: 978080 (C4 (Web Text))
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7231. Min Range: -2.7231
Max Act: 2.5141. Min Act: -0.1700
Data Index: 299233 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7231. Min Range: -2.7231
Max Act: 2.4979. Min Act: -0.1700
Data Index: 447683 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7231. Min Range: -2.7231
Max Act: 2.5141. Min Act: -0.1700
Data Index: 698541 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7231. Min Range: -2.7231
Max Act: 2.5302. Min Act: -0.1700
Data Index: 867656 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #19