Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1195 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.6482. Min Range: -4.6482
Max Act: 4.6482. Min Act: -0.1700
Data Index: 134900 (C4 (Web Text))
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6482. Min Range: -4.6482
Max Act: 4.4919. Min Act: -0.1700
Data Index: 63355 (C4 (Web Text))
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6482. Min Range: -4.6482
Max Act: 4.5232. Min Act: -0.1700
Data Index: 824282 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6482. Min Range: -4.6482
Max Act: 4.5544. Min Act: -0.1700
Data Index: 541996 (C4 (Web Text))
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6482. Min Range: -4.6482
Max Act: 4.4919. Min Act: -0.1700
Data Index: 802624 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6482. Min Range: -4.6482
Max Act: 4.5544. Min Act: -0.1700
Data Index: 941921 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6482. Min Range: -4.6482
Max Act: 4.4607. Min Act: -0.1700
Data Index: 1296403 (C4 (Web Text))
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6482. Min Range: -4.6482
Max Act: 4.5232. Min Act: -0.1700
Data Index: 567995 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6482. Min Range: -4.6482
Max Act: 4.4919. Min Act: -0.1700
Data Index: 979567 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6482. Min Range: -4.6482
Max Act: 4.4607. Min Act: -0.1700
Data Index: 213090 (C4 (Web Text))
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6482. Min Range: -4.6482
Max Act: 4.4607. Min Act: -0.1700
Data Index: 557102 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6482. Min Range: -4.6482
Max Act: 4.4919. Min Act: -0.1700
Data Index: 1341853 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6482. Min Range: -4.6482
Max Act: 4.4294. Min Act: -0.1700
Data Index: 102342 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6482. Min Range: -4.6482
Max Act: 4.3982. Min Act: -0.1700
Data Index: 414996 (C4 (Web Text))
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6482. Min Range: -4.6482
Max Act: 4.4607. Min Act: -0.1700
Data Index: 255062 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6482. Min Range: -4.6482
Max Act: 4.3669. Min Act: -0.1700
Data Index: 552701 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6482. Min Range: -4.6482
Max Act: 4.3982. Min Act: -0.1700
Data Index: 567431 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6482. Min Range: -4.6482
Max Act: 4.3669. Min Act: -0.1700
Data Index: 1101690 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6482. Min Range: -4.6482
Max Act: 4.3357. Min Act: -0.1700
Data Index: 25599 (C4 (Web Text))
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6482. Min Range: -4.6482
Max Act: 4.3669. Min Act: -0.1700
Data Index: 223447 (C4 (Web Text))
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19