Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 972 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.8457. Min Range: -2.8457
Max Act: 2.8457. Min Act: -0.1700
Data Index: 328166 (C4 (Web Text))
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8457. Min Range: -2.8457
Max Act: 2.8298. Min Act: -0.1700
Data Index: 122778 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8457. Min Range: -2.8457
Max Act: 2.7342. Min Act: -0.1700
Data Index: 525263 (C4 (Web Text))
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8457. Min Range: -2.8457
Max Act: 2.7342. Min Act: -0.1700
Data Index: 1247476 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8457. Min Range: -2.8457
Max Act: 2.6862. Min Act: -0.1700
Data Index: 422815 (C4 (Web Text))
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8457. Min Range: -2.8457
Max Act: 2.7022. Min Act: -0.1700
Data Index: 841510 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8457. Min Range: -2.8457
Max Act: 2.7022. Min Act: -0.1700
Data Index: 1146768 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8457. Min Range: -2.8457
Max Act: 2.6702. Min Act: -0.1700
Data Index: 1184102 (C4 (Web Text))
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8457. Min Range: -2.8457
Max Act: 2.6862. Min Act: -0.1700
Data Index: 118784 (C4 (Web Text))
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8457. Min Range: -2.8457
Max Act: 2.6862. Min Act: -0.1700
Data Index: 1063158 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8457. Min Range: -2.8457
Max Act: 2.6702. Min Act: -0.1700
Data Index: 1289689 (C4 (Web Text))
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8457. Min Range: -2.8457
Max Act: 2.6541. Min Act: -0.1700
Data Index: 1016086 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8457. Min Range: -2.8457
Max Act: 2.6541. Min Act: -0.1700
Data Index: 1077305 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8457. Min Range: -2.8457
Max Act: 2.6862. Min Act: -0.1700
Data Index: 204921 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8457. Min Range: -2.8457
Max Act: 2.6541. Min Act: -0.1700
Data Index: 309784 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8457. Min Range: -2.8457
Max Act: 2.6702. Min Act: -0.1700
Data Index: 153197 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8457. Min Range: -2.8457
Max Act: 2.6541. Min Act: -0.1700
Data Index: 692448 (C4 (Web Text))
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8457. Min Range: -2.8457
Max Act: 2.6541. Min Act: -0.1700
Data Index: 941093 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8457. Min Range: -2.8457
Max Act: 2.6381. Min Act: -0.1700
Data Index: 225505 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8457. Min Range: -2.8457
Max Act: 2.6541. Min Act: -0.1700
Data Index: 95467 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19