Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 0 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.7669. Min Range: -4.7669
Max Act: 4.7669. Min Act: -0.1700
Data Index: 220119 (C4 (Web Text))
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7669. Min Range: -4.7669
Max Act: 4.7357. Min Act: -0.1700
Data Index: 1149159 (C4 (Web Text))
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7669. Min Range: -4.7669
Max Act: 4.7044. Min Act: -0.1700
Data Index: 111662 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7669. Min Range: -4.7669
Max Act: 4.6419. Min Act: -0.1700
Data Index: 268570 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7669. Min Range: -4.7669
Max Act: 4.6732. Min Act: -0.1700
Data Index: 287383 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7669. Min Range: -4.7669
Max Act: 4.6419. Min Act: -0.1700
Data Index: 462568 (C4 (Web Text))
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7669. Min Range: -4.7669
Max Act: 4.6107. Min Act: -0.1700
Data Index: 1165529 (C4 (Web Text))
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7669. Min Range: -4.7669
Max Act: 4.6107. Min Act: -0.1700
Data Index: 125049 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7669. Min Range: -4.7669
Max Act: 4.6107. Min Act: -0.1700
Data Index: 746108 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7669. Min Range: -4.7669
Max Act: 4.5794. Min Act: -0.1700
Data Index: 1009427 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7669. Min Range: -4.7669
Max Act: 4.5794. Min Act: -0.1700
Data Index: 876873 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7669. Min Range: -4.7669
Max Act: 4.5794. Min Act: -0.1700
Data Index: 53008 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7669. Min Range: -4.7669
Max Act: 4.5794. Min Act: -0.1700
Data Index: 614268 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7669. Min Range: -4.7669
Max Act: 4.5794. Min Act: -0.1700
Data Index: 1149599 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7669. Min Range: -4.7669
Max Act: 4.5482. Min Act: -0.1700
Data Index: 825054 (C4 (Web Text))
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7669. Min Range: -4.7669
Max Act: 4.5482. Min Act: -0.1700
Data Index: 636802 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7669. Min Range: -4.7669
Max Act: 4.5482. Min Act: -0.1700
Data Index: 780806 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7669. Min Range: -4.7669
Max Act: 4.5169. Min Act: -0.1700
Data Index: 850169 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7669. Min Range: -4.7669
Max Act: 4.5794. Min Act: -0.1700
Data Index: 1344033 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7669. Min Range: -4.7669
Max Act: 4.4857. Min Act: -0.1700
Data Index: 738025 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19