Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 38 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.4507. Min Range: -2.4507
Max Act: 2.4507. Min Act: -0.1700
Data Index: 553655 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4507. Min Range: -2.4507
Max Act: 2.3692. Min Act: -0.1700
Data Index: 336163 (C4 (Web Text))
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4507. Min Range: -2.4507
Max Act: 2.3528. Min Act: -0.1700
Data Index: 730114 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4507. Min Range: -2.4507
Max Act: 2.3528. Min Act: -0.1700
Data Index: 191156 (C4 (Web Text))
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4507. Min Range: -2.4507
Max Act: 2.3364. Min Act: -0.1700
Data Index: 324824 (C4 (Web Text))
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4507. Min Range: -2.4507
Max Act: 2.3364. Min Act: -0.1700
Data Index: 836944 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4507. Min Range: -2.4507
Max Act: 2.3200. Min Act: -0.1700
Data Index: 838833 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4507. Min Range: -2.4507
Max Act: 2.3200. Min Act: -0.1700
Data Index: 1056528 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4507. Min Range: -2.4507
Max Act: 2.3200. Min Act: -0.1700
Data Index: 150887 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4507. Min Range: -2.4507
Max Act: 2.3200. Min Act: -0.1700
Data Index: 189567 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4507. Min Range: -2.4507
Max Act: 2.3200. Min Act: -0.1700
Data Index: 511774 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4507. Min Range: -2.4507
Max Act: 2.3036. Min Act: -0.1700
Data Index: 1618168 (Python Code)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4507. Min Range: -2.4507
Max Act: 2.3036. Min Act: -0.1700
Data Index: 656113 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4507. Min Range: -2.4507
Max Act: 2.3036. Min Act: -0.1700
Data Index: 1023097 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4507. Min Range: -2.4507
Max Act: 2.3036. Min Act: -0.1700
Data Index: 30875 (C4 (Web Text))
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4507. Min Range: -2.4507
Max Act: 2.3036. Min Act: -0.1700
Data Index: 1049514 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4507. Min Range: -2.4507
Max Act: 2.2871. Min Act: -0.1700
Data Index: 444068 (C4 (Web Text))
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4507. Min Range: -2.4507
Max Act: 2.2707. Min Act: -0.1700
Data Index: 1155830 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4507. Min Range: -2.4507
Max Act: 2.2542. Min Act: -0.1700
Data Index: 700626 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4507. Min Range: -2.4507
Max Act: 2.2707. Min Act: -0.1700
Data Index: 653529 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19