Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 292 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.7861. Min Range: -2.7861
Max Act: 2.7861. Min Act: -0.1700
Data Index: 1152826 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7861. Min Range: -2.7861
Max Act: 2.7701. Min Act: -0.1700
Data Index: 72352 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7861. Min Range: -2.7861
Max Act: 2.7222. Min Act: -0.1700
Data Index: 1353408 (C4 (Web Text))
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7861. Min Range: -2.7861
Max Act: 2.7222. Min Act: -0.1700
Data Index: 751241 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7861. Min Range: -2.7861
Max Act: 2.6902. Min Act: -0.1700
Data Index: 1144935 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7861. Min Range: -2.7861
Max Act: 2.6902. Min Act: -0.1700
Data Index: 192141 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7861. Min Range: -2.7861
Max Act: 2.6582. Min Act: -0.1700
Data Index: 439329 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7861. Min Range: -2.7861
Max Act: 2.6582. Min Act: -0.1700
Data Index: 300448 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7861. Min Range: -2.7861
Max Act: 2.6582. Min Act: -0.1700
Data Index: 417572 (C4 (Web Text))
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7861. Min Range: -2.7861
Max Act: 2.6421. Min Act: -0.1700
Data Index: 1212470 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7861. Min Range: -2.7861
Max Act: 2.6421. Min Act: -0.1700
Data Index: 705828 (C4 (Web Text))
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7861. Min Range: -2.7861
Max Act: 2.6261. Min Act: -0.1700
Data Index: 931497 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7861. Min Range: -2.7861
Max Act: 2.6261. Min Act: -0.1700
Data Index: 1028487 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7861. Min Range: -2.7861
Max Act: 2.6261. Min Act: -0.1700
Data Index: 261850 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7861. Min Range: -2.7861
Max Act: 2.6261. Min Act: -0.1700
Data Index: 131153 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7861. Min Range: -2.7861
Max Act: 2.6261. Min Act: -0.1700
Data Index: 863539 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7861. Min Range: -2.7861
Max Act: 2.6100. Min Act: -0.1700
Data Index: 878995 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7861. Min Range: -2.7861
Max Act: 2.6100. Min Act: -0.1700
Data Index: 964487 (C4 (Web Text))
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7861. Min Range: -2.7861
Max Act: 2.5778. Min Act: -0.1700
Data Index: 1636418 (Python Code)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7861. Min Range: -2.7861
Max Act: 2.5939. Min Act: -0.1700
Data Index: 824293 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19