Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1941 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.3529. Min Range: -4.3529
Max Act: 4.3529. Min Act: -0.1700
Data Index: 667078 (C4 (Web Text))
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3529. Min Range: -4.3529
Max Act: 4.1341. Min Act: -0.1700
Data Index: 776449 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3529. Min Range: -4.3529
Max Act: 4.2279. Min Act: -0.1700
Data Index: 836541 (C4 (Web Text))
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3529. Min Range: -4.3529
Max Act: 4.1966. Min Act: -0.1700
Data Index: 1295254 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3529. Min Range: -4.3529
Max Act: 4.1654. Min Act: -0.1700
Data Index: 761084 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3529. Min Range: -4.3529
Max Act: 4.1341. Min Act: -0.1700
Data Index: 1584600 (Python Code)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3529. Min Range: -4.3529
Max Act: 4.1341. Min Act: -0.1700
Data Index: 810954 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3529. Min Range: -4.3529
Max Act: 4.1654. Min Act: -0.1700
Data Index: 660054 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3529. Min Range: -4.3529
Max Act: 4.1341. Min Act: -0.1700
Data Index: 519089 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3529. Min Range: -4.3529
Max Act: 4.1028. Min Act: -0.1700
Data Index: 1462615 (Python Code)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3529. Min Range: -4.3529
Max Act: 4.0091. Min Act: -0.1700
Data Index: 170463 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3529. Min Range: -4.3529
Max Act: 4.0716. Min Act: -0.1700
Data Index: 1285384 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3529. Min Range: -4.3529
Max Act: 4.0716. Min Act: -0.1700
Data Index: 858670 (C4 (Web Text))
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3529. Min Range: -4.3529
Max Act: 4.0716. Min Act: -0.1700
Data Index: 496848 (C4 (Web Text))
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3529. Min Range: -4.3529
Max Act: 4.0403. Min Act: -0.1700
Data Index: 571891 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3529. Min Range: -4.3529
Max Act: 3.9778. Min Act: -0.1700
Data Index: 638604 (C4 (Web Text))
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3529. Min Range: -4.3529
Max Act: 4.0403. Min Act: -0.1700
Data Index: 392846 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3529. Min Range: -4.3529
Max Act: 3.9465. Min Act: -0.1700
Data Index: 443702 (C4 (Web Text))
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3529. Min Range: -4.3529
Max Act: 4.0091. Min Act: -0.1700
Data Index: 985999 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3529. Min Range: -4.3529
Max Act: 4.0403. Min Act: -0.1700
Data Index: 429380 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19