Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 3894 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 2.3436. Min Range: -2.3436
Max Act: 2.3436. Min Act: -0.0001
Data Index: 130816 (The Pile)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3436. Min Range: -2.3436
Max Act: 2.1489. Min Act: -0.0001
Data Index: 103234 (The Pile)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3436. Min Range: -2.3436
Max Act: 2.1391. Min Act: -0.0001
Data Index: 1059577 (The Pile)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3436. Min Range: -2.3436
Max Act: 1.9414. Min Act: -0.0001
Data Index: 894762 (The Pile)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3436. Min Range: -2.3436
Max Act: 2.0821. Min Act: -0.0001
Data Index: 1581013 (The Pile)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3436. Min Range: -2.3436
Max Act: 2.0114. Min Act: -0.0001
Data Index: 1577418 (The Pile)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3436. Min Range: -2.3436
Max Act: 1.9120. Min Act: -0.0001
Data Index: 1951638 (The Pile)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3436. Min Range: -2.3436
Max Act: 1.9992. Min Act: -0.0001
Data Index: 196635 (The Pile)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3436. Min Range: -2.3436
Max Act: 1.7449. Min Act: -0.0001
Data Index: 1336082 (The Pile)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3436. Min Range: -2.3436
Max Act: 2.0189. Min Act: -0.0001
Data Index: 858300 (The Pile)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3436. Min Range: -2.3436
Max Act: 1.8927. Min Act: -0.0001
Data Index: 1152818 (The Pile)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3436. Min Range: -2.3436
Max Act: 1.9026. Min Act: -0.0001
Data Index: 989185 (The Pile)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3436. Min Range: -2.3436
Max Act: 1.8792. Min Act: -0.0001
Data Index: 202138 (The Pile)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3436. Min Range: -2.3436
Max Act: 1.7754. Min Act: -0.0001
Data Index: 574987 (The Pile)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3436. Min Range: -2.3436
Max Act: 1.8573. Min Act: -0.0001
Data Index: 871643 (The Pile)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3436. Min Range: -2.3436
Max Act: 1.9449. Min Act: -0.0001
Data Index: 1128396 (The Pile)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3436. Min Range: -2.3436
Max Act: 1.7253. Min Act: -0.0001
Data Index: 1743840 (The Pile)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3436. Min Range: -2.3436
Max Act: 1.6538. Min Act: -0.0001
Data Index: 25875 (The Pile)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3436. Min Range: -2.3436
Max Act: 1.8799. Min Act: -0.0001
Data Index: 584411 (The Pile)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3436. Min Range: -2.3436
Max Act: 1.8851. Min Act: -0.0001
Data Index: 1510926 (The Pile)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19