Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 580 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.6805. Min Range: -4.6805
Max Act: 4.6805. Min Act: -0.1700
Data Index: 376308 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6805. Min Range: -4.6805
Max Act: 4.6493. Min Act: -0.1700
Data Index: 460934 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6805. Min Range: -4.6805
Max Act: 4.5868. Min Act: -0.1700
Data Index: 1338067 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6805. Min Range: -4.6805
Max Act: 4.5868. Min Act: -0.1700
Data Index: 148081 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6805. Min Range: -4.6805
Max Act: 4.5868. Min Act: -0.1700
Data Index: 878514 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6805. Min Range: -4.6805
Max Act: 4.4930. Min Act: -0.1700
Data Index: 1067627 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6805. Min Range: -4.6805
Max Act: 4.5243. Min Act: -0.1700
Data Index: 1261466 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6805. Min Range: -4.6805
Max Act: 4.4930. Min Act: -0.1700
Data Index: 1020070 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6805. Min Range: -4.6805
Max Act: 4.5243. Min Act: -0.1700
Data Index: 274290 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6805. Min Range: -4.6805
Max Act: 4.4930. Min Act: -0.1700
Data Index: 1094194 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6805. Min Range: -4.6805
Max Act: 4.5243. Min Act: -0.1700
Data Index: 318137 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6805. Min Range: -4.6805
Max Act: 4.5243. Min Act: -0.1700
Data Index: 1228102 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6805. Min Range: -4.6805
Max Act: 4.4618. Min Act: -0.1700
Data Index: 727019 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6805. Min Range: -4.6805
Max Act: 4.4618. Min Act: -0.1700
Data Index: 669841 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6805. Min Range: -4.6805
Max Act: 4.4305. Min Act: -0.1700
Data Index: 1220241 (C4 (Web Text))
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6805. Min Range: -4.6805
Max Act: 4.3992. Min Act: -0.1700
Data Index: 343970 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6805. Min Range: -4.6805
Max Act: 4.4618. Min Act: -0.1700
Data Index: 910341 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6805. Min Range: -4.6805
Max Act: 4.3992. Min Act: -0.1700
Data Index: 870238 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6805. Min Range: -4.6805
Max Act: 4.4305. Min Act: -0.1700
Data Index: 775131 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6805. Min Range: -4.6805
Max Act: 4.3992. Min Act: -0.1700
Data Index: 837682 (C4 (Web Text))
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #19