Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 128 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.9127. Min Range: -4.9127
Max Act: 4.8814. Min Act: -0.1700
Data Index: 823948 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9127. Min Range: -4.9127
Max Act: 4.9127. Min Act: -0.1700
Data Index: 681197 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9127. Min Range: -4.9127
Max Act: 4.8502. Min Act: -0.1700
Data Index: 843452 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9127. Min Range: -4.9127
Max Act: 4.8189. Min Act: -0.1700
Data Index: 871962 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9127. Min Range: -4.9127
Max Act: 4.7877. Min Act: -0.1700
Data Index: 308835 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9127. Min Range: -4.9127
Max Act: 4.7564. Min Act: -0.1700
Data Index: 478438 (C4 (Web Text))
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9127. Min Range: -4.9127
Max Act: 4.7252. Min Act: -0.1700
Data Index: 1267202 (C4 (Web Text))
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9127. Min Range: -4.9127
Max Act: 4.7877. Min Act: -0.1700
Data Index: 277332 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9127. Min Range: -4.9127
Max Act: 4.7252. Min Act: -0.1700
Data Index: 103714 (C4 (Web Text))
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9127. Min Range: -4.9127
Max Act: 4.6939. Min Act: -0.1700
Data Index: 1241798 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9127. Min Range: -4.9127
Max Act: 4.6627. Min Act: -0.1700
Data Index: 621066 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9127. Min Range: -4.9127
Max Act: 4.6939. Min Act: -0.1700
Data Index: 658408 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9127. Min Range: -4.9127
Max Act: 4.7252. Min Act: -0.1700
Data Index: 99371 (C4 (Web Text))
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9127. Min Range: -4.9127
Max Act: 4.6002. Min Act: -0.1700
Data Index: 506666 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9127. Min Range: -4.9127
Max Act: 4.6314. Min Act: -0.1700
Data Index: 187805 (C4 (Web Text))
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9127. Min Range: -4.9127
Max Act: 4.6002. Min Act: -0.1700
Data Index: 160808 (C4 (Web Text))
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9127. Min Range: -4.9127
Max Act: 4.6627. Min Act: -0.1700
Data Index: 1087832 (C4 (Web Text))
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9127. Min Range: -4.9127
Max Act: 4.6314. Min Act: -0.1700
Data Index: 720702 (C4 (Web Text))
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9127. Min Range: -4.9127
Max Act: 4.6002. Min Act: -0.1700
Data Index: 656 (C4 (Web Text))
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9127. Min Range: -4.9127
Max Act: 4.6002. Min Act: -0.1700
Data Index: 291964 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #19