Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 7 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 6.5531. Min Range: -6.5531
Max Act: 6.5531. Min Act: -0.1700
Data Index: 961758 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5531. Min Range: -6.5531
Max Act: 5.8969. Min Act: -0.1700
Data Index: 319077 (C4 (Web Text))
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5531. Min Range: -6.5531
Max Act: 5.8656. Min Act: -0.1699
Data Index: 1092053 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5531. Min Range: -6.5531
Max Act: 5.8344. Min Act: -0.1700
Data Index: 191097 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5531. Min Range: -6.5531
Max Act: 5.7094. Min Act: -0.1700
Data Index: 516254 (C4 (Web Text))
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5531. Min Range: -6.5531
Max Act: 5.7406. Min Act: -0.1700
Data Index: 377675 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5531. Min Range: -6.5531
Max Act: 5.6156. Min Act: -0.1698
Data Index: 252057 (C4 (Web Text))
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5531. Min Range: -6.5531
Max Act: 5.5531. Min Act: -0.1700
Data Index: 1251887 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5531. Min Range: -6.5531
Max Act: 5.5844. Min Act: -0.1699
Data Index: 124333 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5531. Min Range: -6.5531
Max Act: 5.4906. Min Act: -0.1700
Data Index: 937161 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5531. Min Range: -6.5531
Max Act: 5.6156. Min Act: -0.1700
Data Index: 749740 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5531. Min Range: -6.5531
Max Act: 5.4906. Min Act: -0.1699
Data Index: 492100 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5531. Min Range: -6.5531
Max Act: 5.5219. Min Act: -0.1700
Data Index: 714220 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5531. Min Range: -6.5531
Max Act: 5.4594. Min Act: -0.1700
Data Index: 1195361 (C4 (Web Text))
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5531. Min Range: -6.5531
Max Act: 5.5531. Min Act: -0.1700
Data Index: 1071437 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5531. Min Range: -6.5531
Max Act: 5.4594. Min Act: -0.1700
Data Index: 353386 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5531. Min Range: -6.5531
Max Act: 5.3656. Min Act: -0.1699
Data Index: 773561 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5531. Min Range: -6.5531
Max Act: 5.2719. Min Act: -0.1700
Data Index: 448031 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5531. Min Range: -6.5531
Max Act: 5.3969. Min Act: -0.1700
Data Index: 173219 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5531. Min Range: -6.5531
Max Act: 5.2719. Min Act: -0.1700
Data Index: 312256 (C4 (Web Text))
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19