Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 12 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.8669. Min Range: -2.8669
Max Act: 2.8669. Min Act: -0.1700
Data Index: 851414 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8669. Min Range: -2.8669
Max Act: 2.8511. Min Act: -0.1700
Data Index: 666950 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8669. Min Range: -2.8669
Max Act: 2.8511. Min Act: -0.1700
Data Index: 907164 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8669. Min Range: -2.8669
Max Act: 2.8352. Min Act: -0.1700
Data Index: 15708 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8669. Min Range: -2.8669
Max Act: 2.8192. Min Act: -0.1700
Data Index: 1107578 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8669. Min Range: -2.8669
Max Act: 2.8511. Min Act: -0.1700
Data Index: 281102 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8669. Min Range: -2.8669
Max Act: 2.8192. Min Act: -0.1700
Data Index: 923287 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8669. Min Range: -2.8669
Max Act: 2.8352. Min Act: -0.1700
Data Index: 1194510 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8669. Min Range: -2.8669
Max Act: 2.8033. Min Act: -0.1700
Data Index: 113988 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8669. Min Range: -2.8669
Max Act: 2.8033. Min Act: -0.1700
Data Index: 377190 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8669. Min Range: -2.8669
Max Act: 2.8192. Min Act: -0.1700
Data Index: 207335 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8669. Min Range: -2.8669
Max Act: 2.8192. Min Act: -0.1700
Data Index: 1113929 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8669. Min Range: -2.8669
Max Act: 2.8033. Min Act: -0.1700
Data Index: 396501 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8669. Min Range: -2.8669
Max Act: 2.7715. Min Act: -0.1700
Data Index: 1200976 (C4 (Web Text))
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8669. Min Range: -2.8669
Max Act: 2.7715. Min Act: -0.1700
Data Index: 627809 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8669. Min Range: -2.8669
Max Act: 2.7715. Min Act: -0.1700
Data Index: 373 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8669. Min Range: -2.8669
Max Act: 2.7715. Min Act: -0.1700
Data Index: 1047594 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8669. Min Range: -2.8669
Max Act: 2.8033. Min Act: -0.1700
Data Index: 490077 (C4 (Web Text))
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8669. Min Range: -2.8669
Max Act: 2.8033. Min Act: -0.1700
Data Index: 788312 (C4 (Web Text))
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8669. Min Range: -2.8669
Max Act: 2.8033. Min Act: -0.1700
Data Index: 673418 (C4 (Web Text))
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #19