Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 197 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.8433. Min Act: -0.1700
Data Index: 838616 (C4 (Web Text))
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.8910. Min Act: -0.1699
Data Index: 1025040 (C4 (Web Text))
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.8592. Min Act: -0.1700
Data Index: 120944 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.8274. Min Act: -0.1700
Data Index: 395683 (C4 (Web Text))
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.8115. Min Act: -0.1700
Data Index: 574077 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.7956. Min Act: -0.1700
Data Index: 646982 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.7956. Min Act: -0.1700
Data Index: 495097 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.7796. Min Act: -0.1700
Data Index: 1237639 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.7477. Min Act: -0.1700
Data Index: 1112221 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.7637. Min Act: -0.1700
Data Index: 840127 (C4 (Web Text))
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.7637. Min Act: -0.1700
Data Index: 711745 (C4 (Web Text))
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.7477. Min Act: -0.1700
Data Index: 795219 (C4 (Web Text))
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.7158. Min Act: -0.1700
Data Index: 743095 (C4 (Web Text))
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.7158. Min Act: -0.1700
Data Index: 216216 (C4 (Web Text))
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.7318. Min Act: -0.1700
Data Index: 1102978 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.7477. Min Act: -0.1700
Data Index: 336508 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.7158. Min Act: -0.1700
Data Index: 548289 (C4 (Web Text))
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.6998. Min Act: -0.1700
Data Index: 228894 (C4 (Web Text))
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.7158. Min Act: -0.1700
Data Index: 214807 (C4 (Web Text))
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.7318. Min Act: -0.1700
Data Index: 836857 (C4 (Web Text))
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19