Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 2865 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 0.2863. Min Range: -0.2863
Max Act: 0.2863. Min Act: -0.0003
Data Index: 1322051 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2863. Min Range: -0.2863
Max Act: 0.2525. Min Act: -0.0003
Data Index: 1153408 (The Pile)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2863. Min Range: -0.2863
Max Act: 0.2674. Min Act: -0.0003
Data Index: 818648 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2863. Min Range: -0.2863
Max Act: 0.2583. Min Act: -0.0003
Data Index: 1972767 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2863. Min Range: -0.2863
Max Act: 0.2643. Min Act: -0.0003
Data Index: 1426592 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2863. Min Range: -0.2863
Max Act: 0.2521. Min Act: -0.0003
Data Index: 1860093 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2863. Min Range: -0.2863
Max Act: 0.2605. Min Act: -0.0003
Data Index: 1326448 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2863. Min Range: -0.2863
Max Act: 0.2496. Min Act: -0.0003
Data Index: 304653 (The Pile)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2863. Min Range: -0.2863
Max Act: 0.2368. Min Act: -0.0003
Data Index: 1655073 (The Pile)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2863. Min Range: -0.2863
Max Act: 0.2498. Min Act: -0.0003
Data Index: 448028 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2863. Min Range: -0.2863
Max Act: 0.2453. Min Act: -0.0003
Data Index: 256302 (The Pile)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2863. Min Range: -0.2863
Max Act: 0.2495. Min Act: -0.0003
Data Index: 448298 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2863. Min Range: -0.2863
Max Act: 0.2468. Min Act: -0.0003
Data Index: 74039 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2863. Min Range: -0.2863
Max Act: 0.2388. Min Act: -0.0003
Data Index: 71768 (The Pile)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2863. Min Range: -0.2863
Max Act: 0.2384. Min Act: -0.0003
Data Index: 1840835 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2863. Min Range: -0.2863
Max Act: 0.2354. Min Act: -0.0003
Data Index: 1426509 (The Pile)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2863. Min Range: -0.2863
Max Act: 0.2321. Min Act: -0.0003
Data Index: 1518782 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2863. Min Range: -0.2863
Max Act: 0.2370. Min Act: -0.0003
Data Index: 853844 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2863. Min Range: -0.2863
Max Act: 0.2288. Min Act: -0.0003
Data Index: 1656810 (The Pile)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2863. Min Range: -0.2863
Max Act: 0.2293. Min Act: -0.0003
Data Index: 483152 (The Pile)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19