Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 263 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.7302. Min Range: -2.7302
Max Act: 2.7302. Min Act: -0.1700
Data Index: 170281 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7302. Min Range: -2.7302
Max Act: 2.6501. Min Act: -0.1700
Data Index: 440081 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7302. Min Range: -2.7302
Max Act: 2.6341. Min Act: -0.1700
Data Index: 725645 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7302. Min Range: -2.7302
Max Act: 2.6019. Min Act: -0.1700
Data Index: 320080 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7302. Min Range: -2.7302
Max Act: 2.6019. Min Act: -0.1700
Data Index: 329924 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7302. Min Range: -2.7302
Max Act: 2.5858. Min Act: -0.1700
Data Index: 856955 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7302. Min Range: -2.7302
Max Act: 2.5858. Min Act: -0.1700
Data Index: 995095 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7302. Min Range: -2.7302
Max Act: 2.5858. Min Act: -0.1700
Data Index: 1185037 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7302. Min Range: -2.7302
Max Act: 2.5697. Min Act: -0.1700
Data Index: 1013810 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7302. Min Range: -2.7302
Max Act: 2.5697. Min Act: -0.1700
Data Index: 798463 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7302. Min Range: -2.7302
Max Act: 2.5697. Min Act: -0.1700
Data Index: 406334 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7302. Min Range: -2.7302
Max Act: 2.5858. Min Act: -0.1700
Data Index: 227517 (C4 (Web Text))
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7302. Min Range: -2.7302
Max Act: 2.5697. Min Act: -0.1700
Data Index: 823417 (C4 (Web Text))
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7302. Min Range: -2.7302
Max Act: 2.5213. Min Act: -0.1700
Data Index: 272590 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7302. Min Range: -2.7302
Max Act: 2.5536. Min Act: -0.1700
Data Index: 1223681 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7302. Min Range: -2.7302
Max Act: 2.5536. Min Act: -0.1700
Data Index: 544758 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7302. Min Range: -2.7302
Max Act: 2.5536. Min Act: -0.1700
Data Index: 1006259 (C4 (Web Text))
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7302. Min Range: -2.7302
Max Act: 2.5374. Min Act: -0.1700
Data Index: 770645 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7302. Min Range: -2.7302
Max Act: 2.5213. Min Act: -0.1700
Data Index: 572376 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7302. Min Range: -2.7302
Max Act: 2.5374. Min Act: -0.1700
Data Index: 653689 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #19