Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 13 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.2498. Min Range: -4.2498
Max Act: 4.2498. Min Act: -0.1700
Data Index: 486401 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2498. Min Range: -4.2498
Max Act: 4.2186. Min Act: -0.1700
Data Index: 1130434 (C4 (Web Text))
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2498. Min Range: -4.2498
Max Act: 4.1561. Min Act: -0.1700
Data Index: 1125795 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2498. Min Range: -4.2498
Max Act: 4.1561. Min Act: -0.1700
Data Index: 487481 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2498. Min Range: -4.2498
Max Act: 4.1561. Min Act: -0.1700
Data Index: 1155476 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2498. Min Range: -4.2498
Max Act: 4.1561. Min Act: -0.1700
Data Index: 69061 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2498. Min Range: -4.2498
Max Act: 4.0935. Min Act: -0.1700
Data Index: 796824 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2498. Min Range: -4.2498
Max Act: 4.1561. Min Act: -0.1700
Data Index: 1171250 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2498. Min Range: -4.2498
Max Act: 4.1561. Min Act: -0.1700
Data Index: 925863 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2498. Min Range: -4.2498
Max Act: 4.1561. Min Act: -0.1700
Data Index: 400167 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2498. Min Range: -4.2498
Max Act: 4.0935. Min Act: -0.1700
Data Index: 1283902 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2498. Min Range: -4.2498
Max Act: 4.0935. Min Act: -0.1700
Data Index: 179380 (C4 (Web Text))
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2498. Min Range: -4.2498
Max Act: 4.0935. Min Act: -0.1700
Data Index: 2674 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2498. Min Range: -4.2498
Max Act: 4.1248. Min Act: -0.1700
Data Index: 785985 (C4 (Web Text))
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2498. Min Range: -4.2498
Max Act: 4.0935. Min Act: -0.1700
Data Index: 323436 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2498. Min Range: -4.2498
Max Act: 4.0935. Min Act: -0.1700
Data Index: 856063 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2498. Min Range: -4.2498
Max Act: 4.0623. Min Act: -0.1700
Data Index: 198465 (C4 (Web Text))
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2498. Min Range: -4.2498
Max Act: 4.0623. Min Act: -0.1700
Data Index: 356487 (C4 (Web Text))
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2498. Min Range: -4.2498
Max Act: 4.0623. Min Act: -0.1700
Data Index: 911548 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2498. Min Range: -4.2498
Max Act: 4.0623. Min Act: -0.1700
Data Index: 460096 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19