Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 237 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.9469. Min Range: -3.9469
Max Act: 3.8843. Min Act: -0.1700
Data Index: 289122 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9469. Min Range: -3.9469
Max Act: 3.8843. Min Act: -0.1700
Data Index: 486205 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9469. Min Range: -3.9469
Max Act: 3.9469. Min Act: -0.1700
Data Index: 831788 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9469. Min Range: -3.9469
Max Act: 3.7905. Min Act: -0.1700
Data Index: 272392 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9469. Min Range: -3.9469
Max Act: 3.7905. Min Act: -0.1700
Data Index: 1036238 (C4 (Web Text))
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9469. Min Range: -3.9469
Max Act: 3.7905. Min Act: -0.1700
Data Index: 939197 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9469. Min Range: -3.9469
Max Act: 3.7592. Min Act: -0.1700
Data Index: 90575 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9469. Min Range: -3.9469
Max Act: 3.7279. Min Act: -0.1700
Data Index: 127993 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9469. Min Range: -3.9469
Max Act: 3.7905. Min Act: -0.1700
Data Index: 1205256 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9469. Min Range: -3.9469
Max Act: 3.7905. Min Act: -0.1700
Data Index: 1035801 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9469. Min Range: -3.9469
Max Act: 3.7592. Min Act: -0.1700
Data Index: 383479 (C4 (Web Text))
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9469. Min Range: -3.9469
Max Act: 3.7905. Min Act: -0.1700
Data Index: 1101862 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9469. Min Range: -3.9469
Max Act: 3.7592. Min Act: -0.1700
Data Index: 411870 (C4 (Web Text))
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9469. Min Range: -3.9469
Max Act: 3.6966. Min Act: -0.1700
Data Index: 64386 (C4 (Web Text))
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9469. Min Range: -3.9469
Max Act: 3.7592. Min Act: -0.1700
Data Index: 17469 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9469. Min Range: -3.9469
Max Act: 3.7279. Min Act: -0.1700
Data Index: 405132 (C4 (Web Text))
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9469. Min Range: -3.9469
Max Act: 3.7592. Min Act: -0.1700
Data Index: 844480 (C4 (Web Text))
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9469. Min Range: -3.9469
Max Act: 3.6653. Min Act: -0.1700
Data Index: 357765 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9469. Min Range: -3.9469
Max Act: 3.7279. Min Act: -0.1700
Data Index: 553376 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9469. Min Range: -3.9469
Max Act: 3.7592. Min Act: -0.1700
Data Index: 588261 (C4 (Web Text))
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19