Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1086 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 6.6417. Min Range: -6.6417
Max Act: 6.6417. Min Act: -0.1696
Data Index: 29665 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6417. Min Range: -6.6417
Max Act: 6.6104. Min Act: -0.1688
Data Index: 768770 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6417. Min Range: -6.6417
Max Act: 6.4542. Min Act: -0.1700
Data Index: 802149 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6417. Min Range: -6.6417
Max Act: 6.4229. Min Act: -0.1700
Data Index: 1163469 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6417. Min Range: -6.6417
Max Act: 6.4229. Min Act: -0.1700
Data Index: 67191 (C4 (Web Text))
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6417. Min Range: -6.6417
Max Act: 6.3604. Min Act: -0.1700
Data Index: 363984 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6417. Min Range: -6.6417
Max Act: 6.3292. Min Act: -0.1700
Data Index: 159015 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6417. Min Range: -6.6417
Max Act: 6.3292. Min Act: -0.1700
Data Index: 614749 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6417. Min Range: -6.6417
Max Act: 6.3292. Min Act: -0.1700
Data Index: 334582 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6417. Min Range: -6.6417
Max Act: 6.3604. Min Act: -0.1700
Data Index: 64824 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6417. Min Range: -6.6417
Max Act: 6.3292. Min Act: -0.1700
Data Index: 548669 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6417. Min Range: -6.6417
Max Act: 6.3292. Min Act: -0.1699
Data Index: 1188428 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6417. Min Range: -6.6417
Max Act: 6.3292. Min Act: -0.1700
Data Index: 1011927 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6417. Min Range: -6.6417
Max Act: 6.2354. Min Act: -0.1699
Data Index: 1102496 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6417. Min Range: -6.6417
Max Act: 6.2979. Min Act: -0.1700
Data Index: 706677 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6417. Min Range: -6.6417
Max Act: 6.2667. Min Act: -0.1700
Data Index: 1257352 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6417. Min Range: -6.6417
Max Act: 6.2354. Min Act: -0.1700
Data Index: 1143023 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6417. Min Range: -6.6417
Max Act: 6.2042. Min Act: -0.1700
Data Index: 181972 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6417. Min Range: -6.6417
Max Act: 6.2667. Min Act: -0.1700
Data Index: 303013 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6417. Min Range: -6.6417
Max Act: 6.2354. Min Act: -0.1700
Data Index: 943481 (C4 (Web Text))
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #19