Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1396 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.6765. Min Range: -4.6765
Max Act: 4.6765. Min Act: -0.1700
Data Index: 535432 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6765. Min Range: -4.6765
Max Act: 4.5827. Min Act: -0.1700
Data Index: 1432708 (Python Code)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6765. Min Range: -4.6765
Max Act: 4.4577. Min Act: -0.1700
Data Index: 1617067 (Python Code)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6765. Min Range: -4.6765
Max Act: 4.4890. Min Act: -0.1700
Data Index: 1508864 (Python Code)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6765. Min Range: -4.6765
Max Act: 4.3952. Min Act: -0.1700
Data Index: 1477652 (Python Code)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6765. Min Range: -4.6765
Max Act: 4.3640. Min Act: -0.1699
Data Index: 1614585 (Python Code)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6765. Min Range: -4.6765
Max Act: 4.3640. Min Act: -0.1700
Data Index: 1418591 (Python Code)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6765. Min Range: -4.6765
Max Act: 4.3640. Min Act: -0.1700
Data Index: 1467299 (Python Code)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6765. Min Range: -4.6765
Max Act: 4.3952. Min Act: -0.1700
Data Index: 1428053 (Python Code)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6765. Min Range: -4.6765
Max Act: 4.3327. Min Act: -0.1700
Data Index: 1602656 (Python Code)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6765. Min Range: -4.6765
Max Act: 4.3640. Min Act: -0.1700
Data Index: 1503028 (Python Code)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6765. Min Range: -4.6765
Max Act: 4.3015. Min Act: -0.1700
Data Index: 1372736 (Python Code)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6765. Min Range: -4.6765
Max Act: 4.2702. Min Act: -0.1700
Data Index: 1368005 (Python Code)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6765. Min Range: -4.6765
Max Act: 4.2077. Min Act: -0.1700
Data Index: 1618049 (Python Code)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6765. Min Range: -4.6765
Max Act: 4.2389. Min Act: -0.1700
Data Index: 1634630 (Python Code)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6765. Min Range: -4.6765
Max Act: 4.2389. Min Act: -0.1700
Data Index: 1052956 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6765. Min Range: -4.6765
Max Act: 4.2077. Min Act: -0.1700
Data Index: 1457167 (Python Code)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6765. Min Range: -4.6765
Max Act: 4.1764. Min Act: -0.1700
Data Index: 1522410 (Python Code)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6765. Min Range: -4.6765
Max Act: 4.2077. Min Act: -0.1700
Data Index: 1521101 (Python Code)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6765. Min Range: -4.6765
Max Act: 4.2077. Min Act: -0.1700
Data Index: 1358054 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19