Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 146 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.6189. Min Range: -4.6189
Max Act: 4.5564. Min Act: -0.1700
Data Index: 534205 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6189. Min Range: -4.6189
Max Act: 4.5564. Min Act: -0.1700
Data Index: 234274 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6189. Min Range: -4.6189
Max Act: 4.6189. Min Act: -0.1700
Data Index: 119786 (C4 (Web Text))
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6189. Min Range: -4.6189
Max Act: 4.5564. Min Act: -0.1700
Data Index: 1223162 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6189. Min Range: -4.6189
Max Act: 4.5252. Min Act: -0.1700
Data Index: 482532 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6189. Min Range: -4.6189
Max Act: 4.5252. Min Act: -0.1700
Data Index: 328324 (C4 (Web Text))
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6189. Min Range: -4.6189
Max Act: 4.4627. Min Act: -0.1700
Data Index: 1110998 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6189. Min Range: -4.6189
Max Act: 4.4627. Min Act: -0.1700
Data Index: 1312004 (C4 (Web Text))
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6189. Min Range: -4.6189
Max Act: 4.4627. Min Act: -0.1700
Data Index: 369552 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6189. Min Range: -4.6189
Max Act: 4.4002. Min Act: -0.1700
Data Index: 1071770 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6189. Min Range: -4.6189
Max Act: 4.4314. Min Act: -0.1700
Data Index: 1221269 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6189. Min Range: -4.6189
Max Act: 4.4314. Min Act: -0.1700
Data Index: 263430 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6189. Min Range: -4.6189
Max Act: 4.4627. Min Act: -0.1700
Data Index: 785247 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6189. Min Range: -4.6189
Max Act: 4.4314. Min Act: -0.1700
Data Index: 1025930 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6189. Min Range: -4.6189
Max Act: 4.4002. Min Act: -0.1700
Data Index: 395311 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6189. Min Range: -4.6189
Max Act: 4.4314. Min Act: -0.1700
Data Index: 687627 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6189. Min Range: -4.6189
Max Act: 4.4002. Min Act: -0.1700
Data Index: 304272 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6189. Min Range: -4.6189
Max Act: 4.4002. Min Act: -0.1700
Data Index: 142458 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6189. Min Range: -4.6189
Max Act: 4.4002. Min Act: -0.1700
Data Index: 877735 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6189. Min Range: -4.6189
Max Act: 4.4314. Min Act: -0.1700
Data Index: 998180 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #19