Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 56 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.8763. Min Range: -4.8763
Max Act: 4.8763. Min Act: -0.1700
Data Index: 17611 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8763. Min Range: -4.8763
Max Act: 4.8450. Min Act: -0.1700
Data Index: 1016012 (C4 (Web Text))
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8763. Min Range: -4.8763
Max Act: 4.8763. Min Act: -0.1700
Data Index: 850172 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8763. Min Range: -4.8763
Max Act: 4.8450. Min Act: -0.1700
Data Index: 1098463 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8763. Min Range: -4.8763
Max Act: 4.8138. Min Act: -0.1700
Data Index: 603827 (C4 (Web Text))
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8763. Min Range: -4.8763
Max Act: 4.8138. Min Act: -0.1700
Data Index: 88477 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8763. Min Range: -4.8763
Max Act: 4.8138. Min Act: -0.1700
Data Index: 1213233 (C4 (Web Text))
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8763. Min Range: -4.8763
Max Act: 4.8138. Min Act: -0.1700
Data Index: 621656 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8763. Min Range: -4.8763
Max Act: 4.8138. Min Act: -0.1700
Data Index: 82872 (C4 (Web Text))
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8763. Min Range: -4.8763
Max Act: 4.7825. Min Act: -0.1700
Data Index: 284000 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8763. Min Range: -4.8763
Max Act: 4.7825. Min Act: -0.1700
Data Index: 361403 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8763. Min Range: -4.8763
Max Act: 4.7513. Min Act: -0.1700
Data Index: 1072086 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8763. Min Range: -4.8763
Max Act: 4.7825. Min Act: -0.1700
Data Index: 932185 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8763. Min Range: -4.8763
Max Act: 4.7200. Min Act: -0.1700
Data Index: 152877 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8763. Min Range: -4.8763
Max Act: 4.7200. Min Act: -0.1700
Data Index: 228711 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8763. Min Range: -4.8763
Max Act: 4.7513. Min Act: -0.1700
Data Index: 173132 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8763. Min Range: -4.8763
Max Act: 4.7513. Min Act: -0.1700
Data Index: 617930 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8763. Min Range: -4.8763
Max Act: 4.7200. Min Act: -0.1700
Data Index: 544283 (C4 (Web Text))
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8763. Min Range: -4.8763
Max Act: 4.7825. Min Act: -0.1700
Data Index: 1051366 (C4 (Web Text))
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8763. Min Range: -4.8763
Max Act: 4.7513. Min Act: -0.1700
Data Index: 1070172 (C4 (Web Text))
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #19