Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2035 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.1425. Min Range: -3.1425
Max Act: 3.1425. Min Act: -0.1700
Data Index: 492874 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1425. Min Range: -3.1425
Max Act: 3.0794. Min Act: -0.1700
Data Index: 1160577 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1425. Min Range: -3.1425
Max Act: 3.0162. Min Act: -0.1700
Data Index: 286196 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1425. Min Range: -3.1425
Max Act: 3.0004. Min Act: -0.1700
Data Index: 1333222 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1425. Min Range: -3.1425
Max Act: 2.9846. Min Act: -0.1700
Data Index: 491138 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1425. Min Range: -3.1425
Max Act: 2.9846. Min Act: -0.1700
Data Index: 1196438 (C4 (Web Text))
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1425. Min Range: -3.1425
Max Act: 2.9688. Min Act: -0.1700
Data Index: 1055007 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1425. Min Range: -3.1425
Max Act: 2.9530. Min Act: -0.1700
Data Index: 1161863 (C4 (Web Text))
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1425. Min Range: -3.1425
Max Act: 2.9530. Min Act: -0.1700
Data Index: 271280 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1425. Min Range: -3.1425
Max Act: 2.9371. Min Act: -0.1700
Data Index: 820971 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1425. Min Range: -3.1425
Max Act: 2.9371. Min Act: -0.1700
Data Index: 872535 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1425. Min Range: -3.1425
Max Act: 2.9213. Min Act: -0.1700
Data Index: 917260 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1425. Min Range: -3.1425
Max Act: 2.9054. Min Act: -0.1700
Data Index: 1498648 (Python Code)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1425. Min Range: -3.1425
Max Act: 2.9054. Min Act: -0.1700
Data Index: 1150325 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1425. Min Range: -3.1425
Max Act: 2.9054. Min Act: -0.1700
Data Index: 792042 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1425. Min Range: -3.1425
Max Act: 2.9054. Min Act: -0.1700
Data Index: 1297992 (C4 (Web Text))
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1425. Min Range: -3.1425
Max Act: 2.9213. Min Act: -0.1700
Data Index: 504901 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1425. Min Range: -3.1425
Max Act: 2.9054. Min Act: -0.1700
Data Index: 462523 (C4 (Web Text))
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1425. Min Range: -3.1425
Max Act: 2.9213. Min Act: -0.1700
Data Index: 19297 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1425. Min Range: -3.1425
Max Act: 2.9054. Min Act: -0.1700
Data Index: 606859 (C4 (Web Text))
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19