Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 32 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.6666. Min Range: -4.6666
Max Act: 4.6666. Min Act: -0.1700
Data Index: 222671 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6666. Min Range: -4.6666
Max Act: 4.4010. Min Act: -0.1700
Data Index: 48052 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6666. Min Range: -4.6666
Max Act: 4.3385. Min Act: -0.1700
Data Index: 173523 (C4 (Web Text))
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6666. Min Range: -4.6666
Max Act: 4.3385. Min Act: -0.1700
Data Index: 1001047 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6666. Min Range: -4.6666
Max Act: 4.3228. Min Act: -0.1700
Data Index: 860796 (C4 (Web Text))
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6666. Min Range: -4.6666
Max Act: 4.3072. Min Act: -0.1700
Data Index: 157539 (C4 (Web Text))
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6666. Min Range: -4.6666
Max Act: 4.2916. Min Act: -0.1700
Data Index: 629153 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6666. Min Range: -4.6666
Max Act: 4.2760. Min Act: -0.1700
Data Index: 1016229 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6666. Min Range: -4.6666
Max Act: 4.2760. Min Act: -0.1700
Data Index: 1328394 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6666. Min Range: -4.6666
Max Act: 4.2760. Min Act: -0.1700
Data Index: 79813 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6666. Min Range: -4.6666
Max Act: 4.2760. Min Act: -0.1700
Data Index: 1140643 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6666. Min Range: -4.6666
Max Act: 4.2603. Min Act: -0.1700
Data Index: 426944 (C4 (Web Text))
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6666. Min Range: -4.6666
Max Act: 4.2291. Min Act: -0.1700
Data Index: 821671 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6666. Min Range: -4.6666
Max Act: 4.2603. Min Act: -0.1700
Data Index: 593269 (C4 (Web Text))
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6666. Min Range: -4.6666
Max Act: 4.2134. Min Act: -0.1700
Data Index: 284069 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6666. Min Range: -4.6666
Max Act: 4.1978. Min Act: -0.1700
Data Index: 624632 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6666. Min Range: -4.6666
Max Act: 4.2447. Min Act: -0.1699
Data Index: 1211840 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6666. Min Range: -4.6666
Max Act: 4.1822. Min Act: -0.1700
Data Index: 403148 (C4 (Web Text))
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6666. Min Range: -4.6666
Max Act: 4.1822. Min Act: -0.1700
Data Index: 881403 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6666. Min Range: -4.6666
Max Act: 4.1509. Min Act: -0.1700
Data Index: 1017923 (C4 (Web Text))
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19