Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1890 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.4604. Min Range: -3.4604
Max Act: 3.4604. Min Act: -0.1700
Data Index: 527429 (C4 (Web Text))
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4604. Min Range: -3.4604
Max Act: 3.4604. Min Act: -0.1700
Data Index: 892925 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4604. Min Range: -3.4604
Max Act: 3.4604. Min Act: -0.1700
Data Index: 414386 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4604. Min Range: -3.4604
Max Act: 3.4447. Min Act: -0.1700
Data Index: 513153 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4604. Min Range: -3.4604
Max Act: 3.3977. Min Act: -0.1700
Data Index: 1306462 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4604. Min Range: -3.4604
Max Act: 3.4134. Min Act: -0.1700
Data Index: 387523 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4604. Min Range: -3.4604
Max Act: 3.3977. Min Act: -0.1700
Data Index: 17147 (C4 (Web Text))
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4604. Min Range: -3.4604
Max Act: 3.3977. Min Act: -0.1700
Data Index: 844594 (C4 (Web Text))
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4604. Min Range: -3.4604
Max Act: 3.4290. Min Act: -0.1700
Data Index: 516466 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4604. Min Range: -3.4604
Max Act: 3.3506. Min Act: -0.1700
Data Index: 901207 (C4 (Web Text))
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4604. Min Range: -3.4604
Max Act: 3.3820. Min Act: -0.1700
Data Index: 820573 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4604. Min Range: -3.4604
Max Act: 3.3349. Min Act: -0.1700
Data Index: 156331 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4604. Min Range: -3.4604
Max Act: 3.3192. Min Act: -0.1700
Data Index: 1252496 (C4 (Web Text))
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4604. Min Range: -3.4604
Max Act: 3.3192. Min Act: -0.1700
Data Index: 1287661 (C4 (Web Text))
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4604. Min Range: -3.4604
Max Act: 3.3349. Min Act: -0.1700
Data Index: 407700 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4604. Min Range: -3.4604
Max Act: 3.3349. Min Act: -0.1700
Data Index: 1269686 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4604. Min Range: -3.4604
Max Act: 3.3506. Min Act: -0.1700
Data Index: 1303029 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4604. Min Range: -3.4604
Max Act: 3.3349. Min Act: -0.1700
Data Index: 852861 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4604. Min Range: -3.4604
Max Act: 3.3349. Min Act: -0.1700
Data Index: 101072 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4604. Min Range: -3.4604
Max Act: 3.3349. Min Act: -0.1700
Data Index: 298024 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19