Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 150 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.7105. Min Range: -2.7105
Max Act: 2.6945. Min Act: -0.1700
Data Index: 58074 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7105. Min Range: -2.7105
Max Act: 2.7105. Min Act: -0.1700
Data Index: 441756 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7105. Min Range: -2.7105
Max Act: 2.6465. Min Act: -0.1700
Data Index: 159140 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7105. Min Range: -2.7105
Max Act: 2.6625. Min Act: -0.1700
Data Index: 735937 (C4 (Web Text))
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7105. Min Range: -2.7105
Max Act: 2.6465. Min Act: -0.1700
Data Index: 1347438 (C4 (Web Text))
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7105. Min Range: -2.7105
Max Act: 2.6304. Min Act: -0.1700
Data Index: 1298953 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7105. Min Range: -2.7105
Max Act: 2.6465. Min Act: -0.1700
Data Index: 544532 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7105. Min Range: -2.7105
Max Act: 2.6304. Min Act: -0.1700
Data Index: 1030595 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7105. Min Range: -2.7105
Max Act: 2.6304. Min Act: -0.1700
Data Index: 261851 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7105. Min Range: -2.7105
Max Act: 2.6143. Min Act: -0.1700
Data Index: 27767 (C4 (Web Text))
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7105. Min Range: -2.7105
Max Act: 2.6143. Min Act: -0.1700
Data Index: 851585 (C4 (Web Text))
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7105. Min Range: -2.7105
Max Act: 2.6304. Min Act: -0.1700
Data Index: 1292764 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7105. Min Range: -2.7105
Max Act: 2.6143. Min Act: -0.1700
Data Index: 365510 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7105. Min Range: -2.7105
Max Act: 2.5982. Min Act: -0.1700
Data Index: 1013939 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7105. Min Range: -2.7105
Max Act: 2.5821. Min Act: -0.1700
Data Index: 943484 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7105. Min Range: -2.7105
Max Act: 2.5821. Min Act: -0.1700
Data Index: 9810 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7105. Min Range: -2.7105
Max Act: 2.5821. Min Act: -0.1700
Data Index: 449557 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7105. Min Range: -2.7105
Max Act: 2.5982. Min Act: -0.1700
Data Index: 648645 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7105. Min Range: -2.7105
Max Act: 2.5982. Min Act: -0.1700
Data Index: 7352 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7105. Min Range: -2.7105
Max Act: 2.5982. Min Act: -0.1700
Data Index: 732994 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19