Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 61 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.8546. Min Range: -2.8546
Max Act: 2.8546. Min Act: -0.1700
Data Index: 1576358 (Python Code)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8546. Min Range: -2.8546
Max Act: 2.7909. Min Act: -0.1700
Data Index: 1425524 (Python Code)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8546. Min Range: -2.8546
Max Act: 2.6631. Min Act: -0.1700
Data Index: 1150196 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8546. Min Range: -2.8546
Max Act: 2.6631. Min Act: -0.1700
Data Index: 1577876 (Python Code)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8546. Min Range: -2.8546
Max Act: 2.6631. Min Act: -0.1700
Data Index: 1021891 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8546. Min Range: -2.8546
Max Act: 2.6470. Min Act: -0.1700
Data Index: 404446 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8546. Min Range: -2.8546
Max Act: 2.6149. Min Act: -0.1700
Data Index: 326229 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8546. Min Range: -2.8546
Max Act: 2.6149. Min Act: -0.1700
Data Index: 1439092 (Python Code)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8546. Min Range: -2.8546
Max Act: 2.6310. Min Act: -0.1700
Data Index: 1419824 (Python Code)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8546. Min Range: -2.8546
Max Act: 2.6149. Min Act: -0.1700
Data Index: 671847 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8546. Min Range: -2.8546
Max Act: 2.6149. Min Act: -0.1700
Data Index: 1033024 (C4 (Web Text))
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8546. Min Range: -2.8546
Max Act: 2.5988. Min Act: -0.1700
Data Index: 1471079 (Python Code)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8546. Min Range: -2.8546
Max Act: 2.5988. Min Act: -0.1700
Data Index: 1555263 (Python Code)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8546. Min Range: -2.8546
Max Act: 2.5988. Min Act: -0.1700
Data Index: 1527773 (Python Code)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8546. Min Range: -2.8546
Max Act: 2.5988. Min Act: -0.1700
Data Index: 1644059 (Python Code)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8546. Min Range: -2.8546
Max Act: 2.6149. Min Act: -0.1700
Data Index: 740714 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8546. Min Range: -2.8546
Max Act: 2.5827. Min Act: -0.1700
Data Index: 843157 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8546. Min Range: -2.8546
Max Act: 2.5988. Min Act: -0.1700
Data Index: 506154 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8546. Min Range: -2.8546
Max Act: 2.5827. Min Act: -0.1700
Data Index: 911019 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8546. Min Range: -2.8546
Max Act: 2.5827. Min Act: -0.1700
Data Index: 1426361 (Python Code)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19