Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3008 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 4.9367. Min Range: -4.9367
Max Act: 4.9367. Min Act: -0.0001
Data Index: 325551 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9367. Min Range: -4.9367
Max Act: 3.3910. Min Act: -0.0001
Data Index: 381380 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9367. Min Range: -4.9367
Max Act: 3.2799. Min Act: -0.0001
Data Index: 530025 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9367. Min Range: -4.9367
Max Act: 3.2752. Min Act: -0.0001
Data Index: 1036199 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9367. Min Range: -4.9367
Max Act: 3.2637. Min Act: -0.0001
Data Index: 712475 (C4 (Web Text))
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9367. Min Range: -4.9367
Max Act: 3.0823. Min Act: -0.0001
Data Index: 141766 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9367. Min Range: -4.9367
Max Act: 3.3004. Min Act: -0.0001
Data Index: 274266 (C4 (Web Text))
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9367. Min Range: -4.9367
Max Act: 3.3016. Min Act: -0.0001
Data Index: 1050490 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9367. Min Range: -4.9367
Max Act: 3.0627. Min Act: -0.0001
Data Index: 852057 (C4 (Web Text))
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9367. Min Range: -4.9367
Max Act: 3.2961. Min Act: -0.0001
Data Index: 10758 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9367. Min Range: -4.9367
Max Act: 2.7432. Min Act: -0.0001
Data Index: 537828 (C4 (Web Text))
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9367. Min Range: -4.9367
Max Act: 2.8342. Min Act: -0.0001
Data Index: 750996 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9367. Min Range: -4.9367
Max Act: 2.6750. Min Act: -0.0001
Data Index: 810782 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9367. Min Range: -4.9367
Max Act: 2.6436. Min Act: -0.0001
Data Index: 1127072 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9367. Min Range: -4.9367
Max Act: 2.6464. Min Act: -0.0001
Data Index: 190586 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9367. Min Range: -4.9367
Max Act: 2.6494. Min Act: -0.0001
Data Index: 653695 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9367. Min Range: -4.9367
Max Act: 2.4585. Min Act: -0.0001
Data Index: 904308 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9367. Min Range: -4.9367
Max Act: 2.6968. Min Act: -0.0001
Data Index: 788820 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9367. Min Range: -4.9367
Max Act: 2.4302. Min Act: -0.0001
Data Index: 43105 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9367. Min Range: -4.9367
Max Act: 2.5517. Min Act: -0.0001
Data Index: 1255542 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #19