Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 65 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.4772. Min Range: -4.4772
Max Act: 4.4772. Min Act: -0.1700
Data Index: 353389 (C4 (Web Text))
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4772. Min Range: -4.4772
Max Act: 4.2272. Min Act: -0.1700
Data Index: 745569 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4772. Min Range: -4.4772
Max Act: 4.2584. Min Act: -0.1700
Data Index: 243354 (C4 (Web Text))
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4772. Min Range: -4.4772
Max Act: 4.2272. Min Act: -0.1700
Data Index: 798989 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4772. Min Range: -4.4772
Max Act: 4.2272. Min Act: -0.1700
Data Index: 1001151 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4772. Min Range: -4.4772
Max Act: 4.2272. Min Act: -0.1700
Data Index: 6346 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4772. Min Range: -4.4772
Max Act: 4.1647. Min Act: -0.1700
Data Index: 546841 (C4 (Web Text))
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4772. Min Range: -4.4772
Max Act: 4.1959. Min Act: -0.1700
Data Index: 230261 (C4 (Web Text))
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4772. Min Range: -4.4772
Max Act: 4.1334. Min Act: -0.1700
Data Index: 821951 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4772. Min Range: -4.4772
Max Act: 4.1334. Min Act: -0.1700
Data Index: 155368 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4772. Min Range: -4.4772
Max Act: 4.1022. Min Act: -0.1700
Data Index: 1010393 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4772. Min Range: -4.4772
Max Act: 4.1334. Min Act: -0.1700
Data Index: 826654 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4772. Min Range: -4.4772
Max Act: 4.1022. Min Act: -0.1700
Data Index: 871657 (C4 (Web Text))
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4772. Min Range: -4.4772
Max Act: 4.1334. Min Act: -0.1700
Data Index: 972809 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4772. Min Range: -4.4772
Max Act: 4.1334. Min Act: -0.1700
Data Index: 293941 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4772. Min Range: -4.4772
Max Act: 4.1022. Min Act: -0.1700
Data Index: 608501 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4772. Min Range: -4.4772
Max Act: 4.1334. Min Act: -0.1700
Data Index: 656567 (C4 (Web Text))
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4772. Min Range: -4.4772
Max Act: 4.1022. Min Act: -0.1700
Data Index: 354571 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4772. Min Range: -4.4772
Max Act: 4.1334. Min Act: -0.1700
Data Index: 594121 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4772. Min Range: -4.4772
Max Act: 4.1022. Min Act: -0.1700
Data Index: 122984 (C4 (Web Text))
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #19