Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1107 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.3933. Min Range: -0.3933
Max Act: 0.3933. Min Act: -0.0001
Data Index: 1274930 (The Pile)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.3933. Min Range: -0.3933
Max Act: 0.3156. Min Act: -0.0001
Data Index: 1290488 (The Pile)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.3933. Min Range: -0.3933
Max Act: 0.3151. Min Act: -0.0001
Data Index: 86693 (The Pile)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.3933. Min Range: -0.3933
Max Act: 0.3270. Min Act: -0.0001
Data Index: 1094194 (The Pile)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.3933. Min Range: -0.3933
Max Act: 0.3179. Min Act: -0.0001
Data Index: 530602 (The Pile)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.3933. Min Range: -0.3933
Max Act: 0.2606. Min Act: -0.0001
Data Index: 1865036 (The Pile)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.3933. Min Range: -0.3933
Max Act: 0.2732. Min Act: -0.0001
Data Index: 825433 (The Pile)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.3933. Min Range: -0.3933
Max Act: 0.3322. Min Act: -0.0001
Data Index: 1557768 (The Pile)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.3933. Min Range: -0.3933
Max Act: 0.2667. Min Act: -0.0001
Data Index: 52943 (The Pile)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.3933. Min Range: -0.3933
Max Act: 0.2696. Min Act: -0.0001
Data Index: 55979 (The Pile)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.3933. Min Range: -0.3933
Max Act: 0.2765. Min Act: -0.0001
Data Index: 1096849 (The Pile)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.3933. Min Range: -0.3933
Max Act: 0.2955. Min Act: -0.0001
Data Index: 1969925 (The Pile)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.3933. Min Range: -0.3933
Max Act: 0.2876. Min Act: -0.0001
Data Index: 1810486 (The Pile)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.3933. Min Range: -0.3933
Max Act: 0.2498. Min Act: -0.0001
Data Index: 1654982 (The Pile)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.3933. Min Range: -0.3933
Max Act: 0.2527. Min Act: -0.0001
Data Index: 277976 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.3933. Min Range: -0.3933
Max Act: 0.2688. Min Act: -0.0001
Data Index: 1048208 (The Pile)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.3933. Min Range: -0.3933
Max Act: 0.2558. Min Act: -0.0001
Data Index: 640925 (The Pile)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.3933. Min Range: -0.3933
Max Act: 0.2612. Min Act: -0.0001
Data Index: 1700615 (The Pile)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.3933. Min Range: -0.3933
Max Act: 0.2322. Min Act: -0.0001
Data Index: 76461 (The Pile)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.3933. Min Range: -0.3933
Max Act: 0.2565. Min Act: -0.0001
Data Index: 1659463 (The Pile)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #19