Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 41 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.9786. Min Range: -2.9786
Max Act: 2.9786. Min Act: -0.1700
Data Index: 459106 (C4 (Web Text))
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9786. Min Range: -2.9786
Max Act: 2.9152. Min Act: -0.1700
Data Index: 114423 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9786. Min Range: -2.9786
Max Act: 2.8676. Min Act: -0.1700
Data Index: 1065057 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9786. Min Range: -2.9786
Max Act: 2.9152. Min Act: -0.1700
Data Index: 462513 (C4 (Web Text))
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9786. Min Range: -2.9786
Max Act: 2.9152. Min Act: -0.1700
Data Index: 447690 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9786. Min Range: -2.9786
Max Act: 2.8835. Min Act: -0.1700
Data Index: 725969 (C4 (Web Text))
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9786. Min Range: -2.9786
Max Act: 2.7721. Min Act: -0.1700
Data Index: 1348459 (C4 (Web Text))
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9786. Min Range: -2.9786
Max Act: 2.8517. Min Act: -0.1700
Data Index: 1071450 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9786. Min Range: -2.9786
Max Act: 2.8835. Min Act: -0.1700
Data Index: 1040812 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9786. Min Range: -2.9786
Max Act: 2.8040. Min Act: -0.1700
Data Index: 1029413 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9786. Min Range: -2.9786
Max Act: 2.8199. Min Act: -0.1700
Data Index: 246167 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9786. Min Range: -2.9786
Max Act: 2.7562. Min Act: -0.1700
Data Index: 284762 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9786. Min Range: -2.9786
Max Act: 2.7402. Min Act: -0.1700
Data Index: 278338 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9786. Min Range: -2.9786
Max Act: 2.7402. Min Act: -0.1700
Data Index: 853038 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9786. Min Range: -2.9786
Max Act: 2.8358. Min Act: -0.1700
Data Index: 739461 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9786. Min Range: -2.9786
Max Act: 2.7721. Min Act: -0.1700
Data Index: 753939 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9786. Min Range: -2.9786
Max Act: 2.8358. Min Act: -0.1700
Data Index: 1211177 (C4 (Web Text))
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9786. Min Range: -2.9786
Max Act: 2.7562. Min Act: -0.1700
Data Index: 1123101 (C4 (Web Text))
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9786. Min Range: -2.9786
Max Act: 2.7721. Min Act: -0.1700
Data Index: 1328578 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9786. Min Range: -2.9786
Max Act: 2.7881. Min Act: -0.1700
Data Index: 658285 (C4 (Web Text))
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #19