Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1985 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.5013. Min Range: -2.5013
Max Act: 2.5013. Min Act: -0.1700
Data Index: 208405 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5013. Min Range: -2.5013
Max Act: 2.4688. Min Act: -0.1700
Data Index: 254503 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5013. Min Range: -2.5013
Max Act: 2.4363. Min Act: -0.1700
Data Index: 289919 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5013. Min Range: -2.5013
Max Act: 2.4363. Min Act: -0.1700
Data Index: 1191815 (C4 (Web Text))
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5013. Min Range: -2.5013
Max Act: 2.4363. Min Act: -0.1700
Data Index: 888093 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5013. Min Range: -2.5013
Max Act: 2.4363. Min Act: -0.1700
Data Index: 1187383 (C4 (Web Text))
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5013. Min Range: -2.5013
Max Act: 2.4363. Min Act: -0.1700
Data Index: 883903 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5013. Min Range: -2.5013
Max Act: 2.4201. Min Act: -0.1700
Data Index: 35999 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5013. Min Range: -2.5013
Max Act: 2.4363. Min Act: -0.1700
Data Index: 1143902 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5013. Min Range: -2.5013
Max Act: 2.4201. Min Act: -0.1700
Data Index: 890685 (C4 (Web Text))
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5013. Min Range: -2.5013
Max Act: 2.4201. Min Act: -0.1700
Data Index: 230618 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5013. Min Range: -2.5013
Max Act: 2.4038. Min Act: -0.1700
Data Index: 784327 (C4 (Web Text))
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5013. Min Range: -2.5013
Max Act: 2.4038. Min Act: -0.1700
Data Index: 202323 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5013. Min Range: -2.5013
Max Act: 2.4038. Min Act: -0.1700
Data Index: 1045978 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5013. Min Range: -2.5013
Max Act: 2.4038. Min Act: -0.1700
Data Index: 441278 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5013. Min Range: -2.5013
Max Act: 2.4038. Min Act: -0.1700
Data Index: 1152028 (C4 (Web Text))
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5013. Min Range: -2.5013
Max Act: 2.4038. Min Act: -0.1700
Data Index: 299603 (C4 (Web Text))
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5013. Min Range: -2.5013
Max Act: 2.4038. Min Act: -0.1700
Data Index: 101141 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5013. Min Range: -2.5013
Max Act: 2.4038. Min Act: -0.1700
Data Index: 769480 (C4 (Web Text))
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5013. Min Range: -2.5013
Max Act: 2.4038. Min Act: -0.1700
Data Index: 354093 (C4 (Web Text))
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #19