Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1972 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 6.4926. Min Range: -6.4926
Max Act: 6.4926. Min Act: -0.1700
Data Index: 96198 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4926. Min Range: -6.4926
Max Act: 6.4301. Min Act: -0.1700
Data Index: 14891 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4926. Min Range: -6.4926
Max Act: 6.3989. Min Act: -0.1700
Data Index: 1578433 (Python Code)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4926. Min Range: -6.4926
Max Act: 6.3051. Min Act: -0.1700
Data Index: 1238649 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4926. Min Range: -6.4926
Max Act: 6.3364. Min Act: -0.1700
Data Index: 551309 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4926. Min Range: -6.4926
Max Act: 6.3051. Min Act: -0.1700
Data Index: 1525094 (Python Code)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4926. Min Range: -6.4926
Max Act: 6.3051. Min Act: -0.1700
Data Index: 1022989 (C4 (Web Text))
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4926. Min Range: -6.4926
Max Act: 6.3051. Min Act: -0.1700
Data Index: 477884 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4926. Min Range: -6.4926
Max Act: 6.2739. Min Act: -0.1700
Data Index: 276001 (C4 (Web Text))
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4926. Min Range: -6.4926
Max Act: 6.3051. Min Act: -0.1700
Data Index: 1097432 (C4 (Web Text))
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4926. Min Range: -6.4926
Max Act: 6.1801. Min Act: -0.1700
Data Index: 1248780 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4926. Min Range: -6.4926
Max Act: 6.1176. Min Act: -0.1700
Data Index: 366228 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4926. Min Range: -6.4926
Max Act: 6.1176. Min Act: -0.1700
Data Index: 360317 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4926. Min Range: -6.4926
Max Act: 6.1176. Min Act: -0.1700
Data Index: 1015051 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4926. Min Range: -6.4926
Max Act: 6.1176. Min Act: -0.1699
Data Index: 837417 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4926. Min Range: -6.4926
Max Act: 6.1176. Min Act: -0.1700
Data Index: 831552 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4926. Min Range: -6.4926
Max Act: 6.0239. Min Act: -0.1699
Data Index: 42615 (C4 (Web Text))
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4926. Min Range: -6.4926
Max Act: 6.2114. Min Act: -0.1700
Data Index: 1179107 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4926. Min Range: -6.4926
Max Act: 6.0239. Min Act: -0.1700
Data Index: 868032 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4926. Min Range: -6.4926
Max Act: 6.0864. Min Act: -0.1700
Data Index: 1095966 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #19