Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1965 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.7264. Min Range: -4.7264
Max Act: 4.7264. Min Act: -0.1700
Data Index: 306533 (C4 (Web Text))
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7264. Min Range: -4.7264
Max Act: 4.6639. Min Act: -0.1700
Data Index: 513243 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7264. Min Range: -4.7264
Max Act: 4.6639. Min Act: -0.1700
Data Index: 292420 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7264. Min Range: -4.7264
Max Act: 4.5701. Min Act: -0.1700
Data Index: 1118794 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7264. Min Range: -4.7264
Max Act: 4.6014. Min Act: -0.1700
Data Index: 1137762 (C4 (Web Text))
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7264. Min Range: -4.7264
Max Act: 4.5076. Min Act: -0.1700
Data Index: 1340904 (C4 (Web Text))
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7264. Min Range: -4.7264
Max Act: 4.5076. Min Act: -0.1700
Data Index: 1235347 (C4 (Web Text))
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7264. Min Range: -4.7264
Max Act: 4.4451. Min Act: -0.1700
Data Index: 344199 (C4 (Web Text))
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7264. Min Range: -4.7264
Max Act: 4.4139. Min Act: -0.1700
Data Index: 1015802 (C4 (Web Text))
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7264. Min Range: -4.7264
Max Act: 4.4451. Min Act: -0.1700
Data Index: 419038 (C4 (Web Text))
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7264. Min Range: -4.7264
Max Act: 4.4139. Min Act: -0.1700
Data Index: 407995 (C4 (Web Text))
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7264. Min Range: -4.7264
Max Act: 4.4451. Min Act: -0.1700
Data Index: 55512 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7264. Min Range: -4.7264
Max Act: 4.3514. Min Act: -0.1700
Data Index: 1335692 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7264. Min Range: -4.7264
Max Act: 4.4451. Min Act: -0.1700
Data Index: 1142088 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7264. Min Range: -4.7264
Max Act: 4.2889. Min Act: -0.1700
Data Index: 273119 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7264. Min Range: -4.7264
Max Act: 4.4139. Min Act: -0.1700
Data Index: 554022 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7264. Min Range: -4.7264
Max Act: 4.3826. Min Act: -0.1700
Data Index: 737546 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7264. Min Range: -4.7264
Max Act: 4.3826. Min Act: -0.1700
Data Index: 754192 (C4 (Web Text))
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7264. Min Range: -4.7264
Max Act: 4.3514. Min Act: -0.1700
Data Index: 335941 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7264. Min Range: -4.7264
Max Act: 4.4139. Min Act: -0.1700
Data Index: 1010920 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #19