Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 79 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.4421. Min Range: -2.4421
Max Act: 2.4421. Min Act: -0.1700
Data Index: 960601 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4421. Min Range: -2.4421
Max Act: 2.3769. Min Act: -0.1700
Data Index: 1077424 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4421. Min Range: -2.4421
Max Act: 2.3442. Min Act: -0.1700
Data Index: 1175539 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4421. Min Range: -2.4421
Max Act: 2.3442. Min Act: -0.1700
Data Index: 61447 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4421. Min Range: -2.4421
Max Act: 2.3114. Min Act: -0.1700
Data Index: 573905 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4421. Min Range: -2.4421
Max Act: 2.3278. Min Act: -0.1700
Data Index: 117063 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4421. Min Range: -2.4421
Max Act: 2.3278. Min Act: -0.1700
Data Index: 171115 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4421. Min Range: -2.4421
Max Act: 2.3114. Min Act: -0.1700
Data Index: 376780 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4421. Min Range: -2.4421
Max Act: 2.2950. Min Act: -0.1700
Data Index: 720112 (C4 (Web Text))
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4421. Min Range: -2.4421
Max Act: 2.2950. Min Act: -0.1700
Data Index: 709657 (C4 (Web Text))
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4421. Min Range: -2.4421
Max Act: 2.3114. Min Act: -0.1700
Data Index: 1300428 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4421. Min Range: -2.4421
Max Act: 2.3114. Min Act: -0.1700
Data Index: 226824 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4421. Min Range: -2.4421
Max Act: 2.2950. Min Act: -0.1700
Data Index: 1258139 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4421. Min Range: -2.4421
Max Act: 2.2785. Min Act: -0.1700
Data Index: 498904 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4421. Min Range: -2.4421
Max Act: 2.2950. Min Act: -0.1700
Data Index: 1147168 (C4 (Web Text))
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4421. Min Range: -2.4421
Max Act: 2.2950. Min Act: -0.1700
Data Index: 460830 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4421. Min Range: -2.4421
Max Act: 2.2950. Min Act: -0.1700
Data Index: 1257010 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4421. Min Range: -2.4421
Max Act: 2.2950. Min Act: -0.1700
Data Index: 150844 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4421. Min Range: -2.4421
Max Act: 2.2785. Min Act: -0.1700
Data Index: 541116 (C4 (Web Text))
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4421. Min Range: -2.4421
Max Act: 2.2950. Min Act: -0.1700
Data Index: 20647 (C4 (Web Text))
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19