Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 817 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.1256. Min Range: -5.1256
Max Act: 5.1256. Min Act: -0.1700
Data Index: 749865 (C4 (Web Text))
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1256. Min Range: -5.1256
Max Act: 5.0006. Min Act: -0.1700
Data Index: 430906 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1256. Min Range: -5.1256
Max Act: 5.0319. Min Act: -0.1700
Data Index: 1225213 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1256. Min Range: -5.1256
Max Act: 4.9694. Min Act: -0.1700
Data Index: 925699 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1256. Min Range: -5.1256
Max Act: 5.0006. Min Act: -0.1700
Data Index: 584019 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1256. Min Range: -5.1256
Max Act: 5.0006. Min Act: -0.1700
Data Index: 748520 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1256. Min Range: -5.1256
Max Act: 4.9694. Min Act: -0.1700
Data Index: 678341 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1256. Min Range: -5.1256
Max Act: 4.9381. Min Act: -0.1700
Data Index: 920374 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1256. Min Range: -5.1256
Max Act: 4.9381. Min Act: -0.1700
Data Index: 210477 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1256. Min Range: -5.1256
Max Act: 4.9069. Min Act: -0.1700
Data Index: 892728 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1256. Min Range: -5.1256
Max Act: 4.9069. Min Act: -0.1700
Data Index: 11065 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1256. Min Range: -5.1256
Max Act: 4.8756. Min Act: -0.1700
Data Index: 965228 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1256. Min Range: -5.1256
Max Act: 4.8444. Min Act: -0.1700
Data Index: 60865 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1256. Min Range: -5.1256
Max Act: 4.8131. Min Act: -0.1700
Data Index: 721047 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1256. Min Range: -5.1256
Max Act: 4.8756. Min Act: -0.1700
Data Index: 771043 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1256. Min Range: -5.1256
Max Act: 4.8444. Min Act: -0.1700
Data Index: 1082846 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1256. Min Range: -5.1256
Max Act: 4.8131. Min Act: -0.1700
Data Index: 1140048 (C4 (Web Text))
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1256. Min Range: -5.1256
Max Act: 4.7819. Min Act: -0.1700
Data Index: 1064986 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1256. Min Range: -5.1256
Max Act: 4.8131. Min Act: -0.1700
Data Index: 243986 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1256. Min Range: -5.1256
Max Act: 4.7819. Min Act: -0.1700
Data Index: 922562 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19