Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 26 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.8623. Min Range: -2.8623
Max Act: 2.8623. Min Act: -0.1700
Data Index: 1328558 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8623. Min Range: -2.8623
Max Act: 2.7508. Min Act: -0.1700
Data Index: 1038141 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8623. Min Range: -2.8623
Max Act: 2.7668. Min Act: -0.1700
Data Index: 1019687 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8623. Min Range: -2.8623
Max Act: 2.7349. Min Act: -0.1700
Data Index: 969411 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8623. Min Range: -2.8623
Max Act: 2.7349. Min Act: -0.1700
Data Index: 113260 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8623. Min Range: -2.8623
Max Act: 2.7189. Min Act: -0.1700
Data Index: 130961 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8623. Min Range: -2.8623
Max Act: 2.7189. Min Act: -0.1700
Data Index: 914251 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8623. Min Range: -2.8623
Max Act: 2.7189. Min Act: -0.1700
Data Index: 787704 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8623. Min Range: -2.8623
Max Act: 2.7029. Min Act: -0.1700
Data Index: 1080715 (C4 (Web Text))
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8623. Min Range: -2.8623
Max Act: 2.6869. Min Act: -0.1700
Data Index: 881556 (C4 (Web Text))
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8623. Min Range: -2.8623
Max Act: 2.6709. Min Act: -0.1700
Data Index: 443292 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8623. Min Range: -2.8623
Max Act: 2.6709. Min Act: -0.1700
Data Index: 665085 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8623. Min Range: -2.8623
Max Act: 2.6709. Min Act: -0.1700
Data Index: 710971 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8623. Min Range: -2.8623
Max Act: 2.6869. Min Act: -0.1700
Data Index: 71092 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8623. Min Range: -2.8623
Max Act: 2.6709. Min Act: -0.1700
Data Index: 493951 (C4 (Web Text))
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8623. Min Range: -2.8623
Max Act: 2.6709. Min Act: -0.1700
Data Index: 562728 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8623. Min Range: -2.8623
Max Act: 2.6548. Min Act: -0.1700
Data Index: 570525 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8623. Min Range: -2.8623
Max Act: 2.6548. Min Act: -0.1700
Data Index: 951926 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8623. Min Range: -2.8623
Max Act: 2.6548. Min Act: -0.1700
Data Index: 172563 (C4 (Web Text))
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8623. Min Range: -2.8623
Max Act: 2.6548. Min Act: -0.1700
Data Index: 503878 (C4 (Web Text))
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19