Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 85 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.5528. Min Range: -2.5528
Max Act: 2.5528. Min Act: -0.1700
Data Index: 1636932 (Python Code)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5528. Min Range: -2.5528
Max Act: 2.5043. Min Act: -0.1695
Data Index: 455522 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5528. Min Range: -2.5528
Max Act: 2.4881. Min Act: -0.1700
Data Index: 1403797 (Python Code)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5528. Min Range: -2.5528
Max Act: 2.4881. Min Act: -0.1700
Data Index: 1364089 (Python Code)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5528. Min Range: -2.5528
Max Act: 2.4556. Min Act: -0.1700
Data Index: 1620593 (Python Code)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5528. Min Range: -2.5528
Max Act: 2.4556. Min Act: -0.1700
Data Index: 1611130 (Python Code)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5528. Min Range: -2.5528
Max Act: 2.4719. Min Act: -0.1658
Data Index: 1505027 (Python Code)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5528. Min Range: -2.5528
Max Act: 2.4394. Min Act: -0.1700
Data Index: 1365218 (Python Code)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5528. Min Range: -2.5528
Max Act: 2.4394. Min Act: -0.1700
Data Index: 1433159 (Python Code)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5528. Min Range: -2.5528
Max Act: 2.4719. Min Act: -0.1699
Data Index: 1560899 (Python Code)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5528. Min Range: -2.5528
Max Act: 2.4394. Min Act: -0.1700
Data Index: 1398647 (Python Code)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5528. Min Range: -2.5528
Max Act: 2.4394. Min Act: -0.1700
Data Index: 1377822 (Python Code)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5528. Min Range: -2.5528
Max Act: 2.4231. Min Act: -0.1700
Data Index: 1549506 (Python Code)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5528. Min Range: -2.5528
Max Act: 2.4556. Min Act: -0.1700
Data Index: 1377013 (Python Code)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5528. Min Range: -2.5528
Max Act: 2.4394. Min Act: -0.1700
Data Index: 1465028 (Python Code)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5528. Min Range: -2.5528
Max Act: 2.4231. Min Act: -0.1700
Data Index: 1460019 (Python Code)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5528. Min Range: -2.5528
Max Act: 2.4068. Min Act: -0.1700
Data Index: 1508985 (Python Code)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5528. Min Range: -2.5528
Max Act: 2.4231. Min Act: -0.1700
Data Index: 1386374 (Python Code)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5528. Min Range: -2.5528
Max Act: 2.4068. Min Act: -0.1700
Data Index: 1567944 (Python Code)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5528. Min Range: -2.5528
Max Act: 2.4068. Min Act: -0.1700
Data Index: 1573512 (Python Code)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19