Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 30 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.2158. Min Range: -4.2158
Max Act: 4.2158. Min Act: -0.1700
Data Index: 1299674 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2158. Min Range: -4.2158
Max Act: 4.1532. Min Act: -0.1700
Data Index: 468680 (C4 (Web Text))
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2158. Min Range: -4.2158
Max Act: 3.9344. Min Act: -0.1700
Data Index: 121411 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2158. Min Range: -4.2158
Max Act: 3.9031. Min Act: -0.1700
Data Index: 816973 (C4 (Web Text))
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2158. Min Range: -4.2158
Max Act: 3.8719. Min Act: -0.1700
Data Index: 81169 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2158. Min Range: -4.2158
Max Act: 3.8406. Min Act: -0.1700
Data Index: 903350 (C4 (Web Text))
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2158. Min Range: -4.2158
Max Act: 3.8093. Min Act: -0.1700
Data Index: 415909 (C4 (Web Text))
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2158. Min Range: -4.2158
Max Act: 3.8093. Min Act: -0.1700
Data Index: 834235 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2158. Min Range: -4.2158
Max Act: 3.8093. Min Act: -0.1700
Data Index: 327543 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2158. Min Range: -4.2158
Max Act: 3.7780. Min Act: -0.1700
Data Index: 1087296 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2158. Min Range: -4.2158
Max Act: 3.8093. Min Act: -0.1700
Data Index: 137804 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2158. Min Range: -4.2158
Max Act: 3.7780. Min Act: -0.1700
Data Index: 550650 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2158. Min Range: -4.2158
Max Act: 3.7780. Min Act: -0.1700
Data Index: 672633 (C4 (Web Text))
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2158. Min Range: -4.2158
Max Act: 3.8093. Min Act: -0.1700
Data Index: 1065136 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2158. Min Range: -4.2158
Max Act: 3.8093. Min Act: -0.1700
Data Index: 318883 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2158. Min Range: -4.2158
Max Act: 3.7467. Min Act: -0.1700
Data Index: 1011912 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2158. Min Range: -4.2158
Max Act: 3.7467. Min Act: -0.1700
Data Index: 734607 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2158. Min Range: -4.2158
Max Act: 3.7154. Min Act: -0.1700
Data Index: 831085 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2158. Min Range: -4.2158
Max Act: 3.7467. Min Act: -0.1700
Data Index: 965326 (C4 (Web Text))
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2158. Min Range: -4.2158
Max Act: 3.7780. Min Act: -0.1700
Data Index: 53902 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19