Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1806 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.6926. Min Range: -4.6926
Max Act: 4.6926. Min Act: -0.1700
Data Index: 1024878 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6926. Min Range: -4.6926
Max Act: 4.6926. Min Act: -0.1700
Data Index: 828807 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6926. Min Range: -4.6926
Max Act: 4.6301. Min Act: -0.1700
Data Index: 394150 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6926. Min Range: -4.6926
Max Act: 4.5988. Min Act: -0.1700
Data Index: 35313 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6926. Min Range: -4.6926
Max Act: 4.5988. Min Act: -0.1700
Data Index: 1061224 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6926. Min Range: -4.6926
Max Act: 4.5363. Min Act: -0.1700
Data Index: 534110 (C4 (Web Text))
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6926. Min Range: -4.6926
Max Act: 4.5051. Min Act: -0.1700
Data Index: 1139774 (C4 (Web Text))
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6926. Min Range: -4.6926
Max Act: 4.5676. Min Act: -0.1700
Data Index: 787394 (C4 (Web Text))
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6926. Min Range: -4.6926
Max Act: 4.5676. Min Act: -0.1700
Data Index: 1000803 (C4 (Web Text))
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6926. Min Range: -4.6926
Max Act: 4.5051. Min Act: -0.1700
Data Index: 647893 (C4 (Web Text))
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6926. Min Range: -4.6926
Max Act: 4.4113. Min Act: -0.1700
Data Index: 426846 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6926. Min Range: -4.6926
Max Act: 4.4113. Min Act: -0.1700
Data Index: 205324 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6926. Min Range: -4.6926
Max Act: 4.4113. Min Act: -0.1700
Data Index: 323018 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6926. Min Range: -4.6926
Max Act: 4.4426. Min Act: -0.1700
Data Index: 375974 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6926. Min Range: -4.6926
Max Act: 4.4426. Min Act: -0.1700
Data Index: 863877 (C4 (Web Text))
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6926. Min Range: -4.6926
Max Act: 4.4426. Min Act: -0.1700
Data Index: 994268 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6926. Min Range: -4.6926
Max Act: 4.4738. Min Act: -0.1700
Data Index: 509472 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6926. Min Range: -4.6926
Max Act: 4.4113. Min Act: -0.1700
Data Index: 504283 (C4 (Web Text))
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6926. Min Range: -4.6926
Max Act: 4.3801. Min Act: -0.1700
Data Index: 638202 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6926. Min Range: -4.6926
Max Act: 4.4113. Min Act: -0.1700
Data Index: 428587 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #19