Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1963 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.7174. Min Range: -2.7174
Max Act: 2.7174. Min Act: -0.1700
Data Index: 144126 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7174. Min Range: -2.7174
Max Act: 2.7014. Min Act: -0.1700
Data Index: 360969 (C4 (Web Text))
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7174. Min Range: -2.7174
Max Act: 2.6694. Min Act: -0.1700
Data Index: 8571 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7174. Min Range: -2.7174
Max Act: 2.6051. Min Act: -0.1700
Data Index: 1151146 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7174. Min Range: -2.7174
Max Act: 2.6212. Min Act: -0.1700
Data Index: 452471 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7174. Min Range: -2.7174
Max Act: 2.6051. Min Act: -0.1700
Data Index: 202723 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7174. Min Range: -2.7174
Max Act: 2.6051. Min Act: -0.1700
Data Index: 614559 (C4 (Web Text))
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7174. Min Range: -2.7174
Max Act: 2.5568. Min Act: -0.1700
Data Index: 910785 (C4 (Web Text))
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7174. Min Range: -2.7174
Max Act: 2.5729. Min Act: -0.1700
Data Index: 1249521 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7174. Min Range: -2.7174
Max Act: 2.5568. Min Act: -0.1700
Data Index: 694197 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7174. Min Range: -2.7174
Max Act: 2.5245. Min Act: -0.1700
Data Index: 817556 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7174. Min Range: -2.7174
Max Act: 2.5245. Min Act: -0.1700
Data Index: 1102816 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7174. Min Range: -2.7174
Max Act: 2.5245. Min Act: -0.1700
Data Index: 814041 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7174. Min Range: -2.7174
Max Act: 2.5083. Min Act: -0.1700
Data Index: 868853 (C4 (Web Text))
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7174. Min Range: -2.7174
Max Act: 2.5083. Min Act: -0.1700
Data Index: 854264 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7174. Min Range: -2.7174
Max Act: 2.5083. Min Act: -0.1700
Data Index: 296422 (C4 (Web Text))
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7174. Min Range: -2.7174
Max Act: 2.5245. Min Act: -0.1700
Data Index: 1264794 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7174. Min Range: -2.7174
Max Act: 2.4921. Min Act: -0.1700
Data Index: 908821 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7174. Min Range: -2.7174
Max Act: 2.5083. Min Act: -0.1700
Data Index: 26876 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7174. Min Range: -2.7174
Max Act: 2.4921. Min Act: -0.1700
Data Index: 822701 (C4 (Web Text))
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #19