Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2047 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.2838. Min Range: -2.2838
Max Act: 2.2838. Min Act: -0.1700
Data Index: 173426 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2838. Min Range: -2.2838
Max Act: 2.2178. Min Act: -0.1700
Data Index: 328461 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2838. Min Range: -2.2838
Max Act: 2.1680. Min Act: -0.1700
Data Index: 1094207 (C4 (Web Text))
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2838. Min Range: -2.2838
Max Act: 2.1097. Min Act: -0.1700
Data Index: 576911 (C4 (Web Text))
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2838. Min Range: -2.2838
Max Act: 2.0929. Min Act: -0.1700
Data Index: 898526 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2838. Min Range: -2.2838
Max Act: 2.0762. Min Act: -0.1700
Data Index: 249529 (C4 (Web Text))
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2838. Min Range: -2.2838
Max Act: 2.0762. Min Act: -0.1700
Data Index: 157675 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2838. Min Range: -2.2838
Max Act: 2.0510. Min Act: -0.1700
Data Index: 1167331 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2838. Min Range: -2.2838
Max Act: 2.0342. Min Act: -0.1700
Data Index: 692539 (C4 (Web Text))
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2838. Min Range: -2.2838
Max Act: 2.0426. Min Act: -0.1700
Data Index: 1326014 (C4 (Web Text))
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2838. Min Range: -2.2838
Max Act: 2.0173. Min Act: -0.1700
Data Index: 75523 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2838. Min Range: -2.2838
Max Act: 2.0089. Min Act: -0.1700
Data Index: 382342 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2838. Min Range: -2.2838
Max Act: 2.0004. Min Act: -0.1700
Data Index: 129600 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2838. Min Range: -2.2838
Max Act: 1.9835. Min Act: -0.1700
Data Index: 436726 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2838. Min Range: -2.2838
Max Act: 1.9835. Min Act: -0.1700
Data Index: 1251752 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2838. Min Range: -2.2838
Max Act: 1.9835. Min Act: -0.1700
Data Index: 65433 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2838. Min Range: -2.2838
Max Act: 1.9835. Min Act: -0.1700
Data Index: 131258 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2838. Min Range: -2.2838
Max Act: 1.9835. Min Act: -0.1695
Data Index: 414411 (C4 (Web Text))
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2838. Min Range: -2.2838
Max Act: 1.9751. Min Act: -0.1700
Data Index: 1024358 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2838. Min Range: -2.2838
Max Act: 1.9497. Min Act: -0.1700
Data Index: 352321 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #19