Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 271 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.9493. Min Range: -2.9493
Max Act: 2.9493. Min Act: -0.1700
Data Index: 1617108 (Python Code)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9493. Min Range: -2.9493
Max Act: 2.9493. Min Act: -0.1700
Data Index: 1563942 (Python Code)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9493. Min Range: -2.9493
Max Act: 2.9335. Min Act: -0.1700
Data Index: 1401146 (Python Code)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9493. Min Range: -2.9493
Max Act: 2.9176. Min Act: -0.1700
Data Index: 1539859 (Python Code)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9493. Min Range: -2.9493
Max Act: 2.9176. Min Act: -0.1700
Data Index: 1519875 (Python Code)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9493. Min Range: -2.9493
Max Act: 2.8859. Min Act: -0.1700
Data Index: 1549249 (Python Code)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9493. Min Range: -2.9493
Max Act: 2.8859. Min Act: -0.1700
Data Index: 1634200 (Python Code)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9493. Min Range: -2.9493
Max Act: 2.8859. Min Act: -0.1700
Data Index: 1435495 (Python Code)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9493. Min Range: -2.9493
Max Act: 2.8541. Min Act: -0.1700
Data Index: 1552202 (Python Code)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9493. Min Range: -2.9493
Max Act: 2.8223. Min Act: -0.1700
Data Index: 1603222 (Python Code)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9493. Min Range: -2.9493
Max Act: 2.8382. Min Act: -0.1700
Data Index: 1620217 (Python Code)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9493. Min Range: -2.9493
Max Act: 2.8382. Min Act: -0.1700
Data Index: 1612085 (Python Code)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9493. Min Range: -2.9493
Max Act: 2.8223. Min Act: -0.1700
Data Index: 1498141 (Python Code)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9493. Min Range: -2.9493
Max Act: 2.8382. Min Act: -0.1700
Data Index: 1645426 (Python Code)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9493. Min Range: -2.9493
Max Act: 2.8064. Min Act: -0.1700
Data Index: 1453921 (Python Code)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9493. Min Range: -2.9493
Max Act: 2.8223. Min Act: -0.1700
Data Index: 1623015 (Python Code)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9493. Min Range: -2.9493
Max Act: 2.8064. Min Act: -0.1700
Data Index: 1621960 (Python Code)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9493. Min Range: -2.9493
Max Act: 2.7905. Min Act: -0.1700
Data Index: 1577729 (Python Code)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9493. Min Range: -2.9493
Max Act: 2.7905. Min Act: -0.1700
Data Index: 1546656 (Python Code)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9493. Min Range: -2.9493
Max Act: 2.8064. Min Act: -0.1700
Data Index: 1396759 (Python Code)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #19