Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3051 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 2.9632. Min Range: -2.9632
Max Act: 2.9632. Min Act: -0.0001
Data Index: 710132 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9632. Min Range: -2.9632
Max Act: 2.8145. Min Act: -0.0001
Data Index: 226781 (C4 (Web Text))
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9632. Min Range: -2.9632
Max Act: 2.6400. Min Act: -0.0001
Data Index: 579602 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9632. Min Range: -2.9632
Max Act: 2.4916. Min Act: -0.0001
Data Index: 1219610 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9632. Min Range: -2.9632
Max Act: 2.4234. Min Act: -0.0001
Data Index: 232966 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9632. Min Range: -2.9632
Max Act: 2.3648. Min Act: -0.0001
Data Index: 178737 (C4 (Web Text))
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9632. Min Range: -2.9632
Max Act: 2.4576. Min Act: -0.0001
Data Index: 752584 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9632. Min Range: -2.9632
Max Act: 2.3473. Min Act: -0.0000
Data Index: 629004 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9632. Min Range: -2.9632
Max Act: 2.3923. Min Act: -0.0001
Data Index: 597540 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9632. Min Range: -2.9632
Max Act: 2.2378. Min Act: -0.0001
Data Index: 545343 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9632. Min Range: -2.9632
Max Act: 2.3426. Min Act: -0.0001
Data Index: 340421 (C4 (Web Text))
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9632. Min Range: -2.9632
Max Act: 2.2669. Min Act: -0.0001
Data Index: 148043 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9632. Min Range: -2.9632
Max Act: 2.2822. Min Act: -0.0001
Data Index: 796747 (C4 (Web Text))
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9632. Min Range: -2.9632
Max Act: 2.2658. Min Act: -0.0001
Data Index: 297180 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9632. Min Range: -2.9632
Max Act: 2.2499. Min Act: -0.0001
Data Index: 413310 (C4 (Web Text))
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9632. Min Range: -2.9632
Max Act: 2.2270. Min Act: -0.0001
Data Index: 673739 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9632. Min Range: -2.9632
Max Act: 2.1182. Min Act: -0.0001
Data Index: 864521 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9632. Min Range: -2.9632
Max Act: 2.0526. Min Act: -0.0001
Data Index: 213107 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9632. Min Range: -2.9632
Max Act: 2.2141. Min Act: -0.0001
Data Index: 502375 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9632. Min Range: -2.9632
Max Act: 2.2006. Min Act: -0.0001
Data Index: 534788 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #19