Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1808 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 3.7481. Min Range: -3.7481
Max Act: 3.7481. Min Act: -0.0000
Data Index: 1808825 (The Pile)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7481. Min Range: -3.7481
Max Act: 1.7892. Min Act: -0.0000
Data Index: 1843819 (The Pile)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7481. Min Range: -3.7481
Max Act: 1.9018. Min Act: -0.0000
Data Index: 1211577 (The Pile)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7481. Min Range: -3.7481
Max Act: 1.8472. Min Act: -0.0000
Data Index: 1030599 (The Pile)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7481. Min Range: -3.7481
Max Act: 1.9196. Min Act: -0.0000
Data Index: 1825571 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7481. Min Range: -3.7481
Max Act: 1.9110. Min Act: -0.0000
Data Index: 642441 (The Pile)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7481. Min Range: -3.7481
Max Act: 1.8956. Min Act: 0.0000
Data Index: 1495853 (The Pile)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7481. Min Range: -3.7481
Max Act: 1.5976. Min Act: -0.0000
Data Index: 362579 (The Pile)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7481. Min Range: -3.7481
Max Act: 1.3794. Min Act: -0.0000
Data Index: 1656758 (The Pile)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7481. Min Range: -3.7481
Max Act: 1.7792. Min Act: -0.0000
Data Index: 930061 (The Pile)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7481. Min Range: -3.7481
Max Act: 1.8637. Min Act: -0.0000
Data Index: 1806014 (The Pile)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7481. Min Range: -3.7481
Max Act: 1.3711. Min Act: -0.0000
Data Index: 1413820 (The Pile)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7481. Min Range: -3.7481
Max Act: 1.5064. Min Act: -0.0000
Data Index: 469279 (The Pile)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7481. Min Range: -3.7481
Max Act: 1.4722. Min Act: -0.0000
Data Index: 735263 (The Pile)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7481. Min Range: -3.7481
Max Act: 1.3345. Min Act: 0.0000
Data Index: 29800 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7481. Min Range: -3.7481
Max Act: 1.4221. Min Act: -0.0000
Data Index: 1582955 (The Pile)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7481. Min Range: -3.7481
Max Act: 1.5078. Min Act: -0.0000
Data Index: 533456 (The Pile)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7481. Min Range: -3.7481
Max Act: 1.2875. Min Act: -0.0000
Data Index: 910731 (The Pile)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7481. Min Range: -3.7481
Max Act: 1.4165. Min Act: -0.0000
Data Index: 1045353 (The Pile)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7481. Min Range: -3.7481
Max Act: 1.4897. Min Act: -0.0000
Data Index: 12574 (The Pile)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19