Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 331 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.7607. Min Range: -4.7607
Max Act: 4.7607. Min Act: -0.1700
Data Index: 309314 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7607. Min Range: -4.7607
Max Act: 4.7607. Min Act: -0.1700
Data Index: 1097443 (C4 (Web Text))
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7607. Min Range: -4.7607
Max Act: 4.5419. Min Act: -0.1700
Data Index: 423620 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7607. Min Range: -4.7607
Max Act: 4.5732. Min Act: -0.1700
Data Index: 625510 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7607. Min Range: -4.7607
Max Act: 4.5107. Min Act: -0.1700
Data Index: 1177279 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7607. Min Range: -4.7607
Max Act: 4.4482. Min Act: -0.1700
Data Index: 611621 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7607. Min Range: -4.7607
Max Act: 4.5419. Min Act: -0.1700
Data Index: 356985 (C4 (Web Text))
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7607. Min Range: -4.7607
Max Act: 4.4482. Min Act: -0.1700
Data Index: 1160395 (C4 (Web Text))
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7607. Min Range: -4.7607
Max Act: 4.3544. Min Act: -0.1700
Data Index: 1197876 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7607. Min Range: -4.7607
Max Act: 4.3857. Min Act: -0.1700
Data Index: 42509 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7607. Min Range: -4.7607
Max Act: 4.3544. Min Act: -0.1700
Data Index: 864839 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7607. Min Range: -4.7607
Max Act: 4.3544. Min Act: -0.1700
Data Index: 1114005 (C4 (Web Text))
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7607. Min Range: -4.7607
Max Act: 4.3232. Min Act: -0.1700
Data Index: 1095351 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7607. Min Range: -4.7607
Max Act: 4.3232. Min Act: -0.1700
Data Index: 651724 (C4 (Web Text))
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7607. Min Range: -4.7607
Max Act: 4.3232. Min Act: -0.1700
Data Index: 120107 (C4 (Web Text))
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7607. Min Range: -4.7607
Max Act: 4.3232. Min Act: -0.1700
Data Index: 415399 (C4 (Web Text))
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7607. Min Range: -4.7607
Max Act: 4.2607. Min Act: -0.1700
Data Index: 1247649 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7607. Min Range: -4.7607
Max Act: 4.3232. Min Act: -0.1700
Data Index: 838199 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7607. Min Range: -4.7607
Max Act: 4.2294. Min Act: -0.1700
Data Index: 537560 (C4 (Web Text))
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7607. Min Range: -4.7607
Max Act: 4.2294. Min Act: -0.1700
Data Index: 313281 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19