Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1662 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.2455. Min Range: -3.2455
Max Act: 3.2455. Min Act: -0.1700
Data Index: 1182336 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2455. Min Range: -3.2455
Max Act: 3.1353. Min Act: -0.1700
Data Index: 813419 (C4 (Web Text))
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2455. Min Range: -3.2455
Max Act: 3.0407. Min Act: -0.1700
Data Index: 123083 (C4 (Web Text))
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2455. Min Range: -3.2455
Max Act: 3.0407. Min Act: -0.1700
Data Index: 864087 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2455. Min Range: -3.2455
Max Act: 2.9775. Min Act: -0.1700
Data Index: 1505092 (Python Code)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2455. Min Range: -3.2455
Max Act: 2.9617. Min Act: -0.1700
Data Index: 699444 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2455. Min Range: -3.2455
Max Act: 2.8983. Min Act: -0.1700
Data Index: 110265 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2455. Min Range: -3.2455
Max Act: 2.8983. Min Act: -0.1700
Data Index: 1453906 (Python Code)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2455. Min Range: -3.2455
Max Act: 2.8824. Min Act: -0.1700
Data Index: 159325 (C4 (Web Text))
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2455. Min Range: -3.2455
Max Act: 2.8824. Min Act: -0.1700
Data Index: 1076896 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2455. Min Range: -3.2455
Max Act: 2.8665. Min Act: -0.1700
Data Index: 886734 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2455. Min Range: -3.2455
Max Act: 2.8506. Min Act: -0.1700
Data Index: 530520 (C4 (Web Text))
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2455. Min Range: -3.2455
Max Act: 2.8029. Min Act: -0.1700
Data Index: 426802 (C4 (Web Text))
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2455. Min Range: -3.2455
Max Act: 2.8188. Min Act: -0.1700
Data Index: 1644322 (Python Code)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2455. Min Range: -3.2455
Max Act: 2.7710. Min Act: -0.1700
Data Index: 462178 (C4 (Web Text))
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2455. Min Range: -3.2455
Max Act: 2.8029. Min Act: -0.1700
Data Index: 1274258 (C4 (Web Text))
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2455. Min Range: -3.2455
Max Act: 2.8188. Min Act: -0.1700
Data Index: 1105248 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2455. Min Range: -3.2455
Max Act: 2.7710. Min Act: -0.1700
Data Index: 34795 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2455. Min Range: -3.2455
Max Act: 2.7391. Min Act: -0.1700
Data Index: 983567 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2455. Min Range: -3.2455
Max Act: 2.6912. Min Act: -0.1700
Data Index: 74527 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #19