Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 74 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.8661. Min Range: -4.8661
Max Act: 4.8661. Min Act: -0.1700
Data Index: 1208341 (C4 (Web Text))
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8661. Min Range: -4.8661
Max Act: 4.8661. Min Act: -0.1700
Data Index: 981590 (C4 (Web Text))
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8661. Min Range: -4.8661
Max Act: 4.8036. Min Act: -0.1700
Data Index: 473757 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8661. Min Range: -4.8661
Max Act: 4.7411. Min Act: -0.1700
Data Index: 640619 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8661. Min Range: -4.8661
Max Act: 4.6161. Min Act: -0.1700
Data Index: 939473 (C4 (Web Text))
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8661. Min Range: -4.8661
Max Act: 4.6942. Min Act: -0.1700
Data Index: 25218 (C4 (Web Text))
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8661. Min Range: -4.8661
Max Act: 4.6474. Min Act: -0.1700
Data Index: 789164 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8661. Min Range: -4.8661
Max Act: 4.6317. Min Act: -0.1700
Data Index: 686666 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8661. Min Range: -4.8661
Max Act: 4.5536. Min Act: -0.1700
Data Index: 750452 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8661. Min Range: -4.8661
Max Act: 4.5692. Min Act: -0.1700
Data Index: 42360 (C4 (Web Text))
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8661. Min Range: -4.8661
Max Act: 4.5067. Min Act: -0.1700
Data Index: 795484 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8661. Min Range: -4.8661
Max Act: 4.5380. Min Act: -0.1700
Data Index: 836948 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8661. Min Range: -4.8661
Max Act: 4.5380. Min Act: -0.1700
Data Index: 1047220 (C4 (Web Text))
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8661. Min Range: -4.8661
Max Act: 4.5380. Min Act: -0.1700
Data Index: 1356963 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8661. Min Range: -4.8661
Max Act: 4.5067. Min Act: -0.1700
Data Index: 694936 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8661. Min Range: -4.8661
Max Act: 4.5849. Min Act: -0.1700
Data Index: 579410 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8661. Min Range: -4.8661
Max Act: 4.5380. Min Act: -0.1700
Data Index: 20646 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8661. Min Range: -4.8661
Max Act: 4.5224. Min Act: -0.1700
Data Index: 862912 (C4 (Web Text))
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8661. Min Range: -4.8661
Max Act: 4.5067. Min Act: -0.1700
Data Index: 1126500 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8661. Min Range: -4.8661
Max Act: 4.5380. Min Act: -0.1700
Data Index: 624024 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #19