Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 58 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.2740. Min Range: -3.2740
Max Act: 3.2740. Min Act: -0.1700
Data Index: 1104246 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2740. Min Range: -3.2740
Max Act: 3.0536. Min Act: -0.1700
Data Index: 275318 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2740. Min Range: -3.2740
Max Act: 3.0693. Min Act: -0.1700
Data Index: 791144 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2740. Min Range: -3.2740
Max Act: 3.0536. Min Act: -0.1700
Data Index: 1051577 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2740. Min Range: -3.2740
Max Act: 2.9745. Min Act: -0.1700
Data Index: 1244209 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2740. Min Range: -3.2740
Max Act: 2.9745. Min Act: -0.1700
Data Index: 803134 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2740. Min Range: -3.2740
Max Act: 2.9745. Min Act: -0.1700
Data Index: 88668 (C4 (Web Text))
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2740. Min Range: -3.2740
Max Act: 2.9270. Min Act: -0.1700
Data Index: 1000775 (C4 (Web Text))
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2740. Min Range: -3.2740
Max Act: 2.8953. Min Act: -0.1700
Data Index: 357161 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2740. Min Range: -3.2740
Max Act: 2.8953. Min Act: -0.1700
Data Index: 1194867 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2740. Min Range: -3.2740
Max Act: 2.8636. Min Act: -0.1700
Data Index: 433918 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2740. Min Range: -3.2740
Max Act: 2.8636. Min Act: -0.1700
Data Index: 1002505 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2740. Min Range: -3.2740
Max Act: 2.8795. Min Act: -0.1700
Data Index: 1190210 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2740. Min Range: -3.2740
Max Act: 2.8477. Min Act: -0.1700
Data Index: 1082346 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2740. Min Range: -3.2740
Max Act: 2.8636. Min Act: -0.1700
Data Index: 1169252 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2740. Min Range: -3.2740
Max Act: 2.8477. Min Act: -0.1700
Data Index: 398596 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2740. Min Range: -3.2740
Max Act: 2.8318. Min Act: -0.1700
Data Index: 1058009 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2740. Min Range: -3.2740
Max Act: 2.8159. Min Act: -0.1700
Data Index: 820711 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2740. Min Range: -3.2740
Max Act: 2.8318. Min Act: -0.1700
Data Index: 460585 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2740. Min Range: -3.2740
Max Act: 2.8000. Min Act: -0.1700
Data Index: 261419 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #19