Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 817 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 2.2364. Min Range: -2.2364
Max Act: 2.2364. Min Act: -0.0001
Data Index: 823643 (The Pile)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2364. Min Range: -2.2364
Max Act: 2.0907. Min Act: -0.0001
Data Index: 252975 (The Pile)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2364. Min Range: -2.2364
Max Act: 1.8836. Min Act: -0.0001
Data Index: 658873 (The Pile)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2364. Min Range: -2.2364
Max Act: 1.9495. Min Act: -0.0001
Data Index: 1299907 (The Pile)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2364. Min Range: -2.2364
Max Act: 1.8083. Min Act: -0.0001
Data Index: 483123 (The Pile)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2364. Min Range: -2.2364
Max Act: 2.0949. Min Act: -0.0001
Data Index: 1371435 (The Pile)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2364. Min Range: -2.2364
Max Act: 1.9843. Min Act: -0.0001
Data Index: 1450877 (The Pile)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2364. Min Range: -2.2364
Max Act: 1.8039. Min Act: -0.0001
Data Index: 445467 (The Pile)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2364. Min Range: -2.2364
Max Act: 1.8029. Min Act: -0.0001
Data Index: 214972 (The Pile)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2364. Min Range: -2.2364
Max Act: 1.8144. Min Act: -0.0001
Data Index: 626421 (The Pile)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2364. Min Range: -2.2364
Max Act: 1.6669. Min Act: -0.0001
Data Index: 691622 (The Pile)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2364. Min Range: -2.2364
Max Act: 1.8273. Min Act: -0.0000
Data Index: 1592658 (The Pile)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2364. Min Range: -2.2364
Max Act: 1.9119. Min Act: -0.0001
Data Index: 1488383 (The Pile)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2364. Min Range: -2.2364
Max Act: 1.7760. Min Act: -0.0001
Data Index: 510014 (The Pile)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2364. Min Range: -2.2364
Max Act: 1.7594. Min Act: -0.0001
Data Index: 333383 (The Pile)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2364. Min Range: -2.2364
Max Act: 1.7294. Min Act: -0.0001
Data Index: 1843693 (The Pile)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2364. Min Range: -2.2364
Max Act: 1.6089. Min Act: -0.0001
Data Index: 104583 (The Pile)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2364. Min Range: -2.2364
Max Act: 1.6612. Min Act: -0.0001
Data Index: 323474 (The Pile)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2364. Min Range: -2.2364
Max Act: 1.6269. Min Act: -0.0001
Data Index: 525310 (The Pile)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2364. Min Range: -2.2364
Max Act: 1.6562. Min Act: -0.0001
Data Index: 306533 (The Pile)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19