Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 103 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.5765. Min Range: -2.5765
Max Act: 2.5765. Min Act: -0.1700
Data Index: 1030179 (C4 (Web Text))
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5765. Min Range: -2.5765
Max Act: 2.3982. Min Act: -0.1700
Data Index: 31162 (C4 (Web Text))
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5765. Min Range: -2.5765
Max Act: 2.4308. Min Act: -0.1700
Data Index: 286414 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5765. Min Range: -2.5765
Max Act: 2.3982. Min Act: -0.1700
Data Index: 1301885 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5765. Min Range: -2.5765
Max Act: 2.4145. Min Act: -0.1700
Data Index: 930294 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5765. Min Range: -2.5765
Max Act: 2.3819. Min Act: -0.1700
Data Index: 1094078 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5765. Min Range: -2.5765
Max Act: 2.3655. Min Act: -0.1700
Data Index: 462816 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5765. Min Range: -2.5765
Max Act: 2.3655. Min Act: -0.1700
Data Index: 945970 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5765. Min Range: -2.5765
Max Act: 2.3655. Min Act: -0.1700
Data Index: 940225 (C4 (Web Text))
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5765. Min Range: -2.5765
Max Act: 2.3655. Min Act: -0.1700
Data Index: 313870 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5765. Min Range: -2.5765
Max Act: 2.3164. Min Act: -0.1700
Data Index: 168323 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5765. Min Range: -2.5765
Max Act: 2.3164. Min Act: -0.1700
Data Index: 484136 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5765. Min Range: -2.5765
Max Act: 2.3164. Min Act: -0.1700
Data Index: 917110 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5765. Min Range: -2.5765
Max Act: 2.3164. Min Act: -0.1700
Data Index: 1143285 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5765. Min Range: -2.5765
Max Act: 2.3164. Min Act: -0.1700
Data Index: 13208 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5765. Min Range: -2.5765
Max Act: 2.3164. Min Act: -0.1700
Data Index: 834562 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5765. Min Range: -2.5765
Max Act: 2.2999. Min Act: -0.1700
Data Index: 438631 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5765. Min Range: -2.5765
Max Act: 2.2999. Min Act: -0.1700
Data Index: 236219 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5765. Min Range: -2.5765
Max Act: 2.2835. Min Act: -0.1700
Data Index: 341489 (C4 (Web Text))
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5765. Min Range: -2.5765
Max Act: 2.2835. Min Act: -0.1700
Data Index: 955470 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19