Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 4040 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.9483. Min Range: -1.9483
Max Act: 1.9483. Min Act: -0.0001
Data Index: 376796 (The Pile)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9483. Min Range: -1.9483
Max Act: 1.6648. Min Act: -0.0001
Data Index: 376997 (The Pile)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9483. Min Range: -1.9483
Max Act: 1.5055. Min Act: -0.0001
Data Index: 1038958 (The Pile)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9483. Min Range: -1.9483
Max Act: 1.5031. Min Act: -0.0001
Data Index: 1377391 (The Pile)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9483. Min Range: -1.9483
Max Act: 1.3580. Min Act: -0.0001
Data Index: 1923232 (The Pile)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9483. Min Range: -1.9483
Max Act: 1.4337. Min Act: -0.0001
Data Index: 965663 (The Pile)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9483. Min Range: -1.9483
Max Act: 1.3505. Min Act: -0.0001
Data Index: 101784 (The Pile)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9483. Min Range: -1.9483
Max Act: 1.4049. Min Act: -0.0001
Data Index: 846742 (The Pile)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9483. Min Range: -1.9483
Max Act: 1.3677. Min Act: -0.0001
Data Index: 491272 (The Pile)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9483. Min Range: -1.9483
Max Act: 1.3496. Min Act: -0.0001
Data Index: 314887 (The Pile)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9483. Min Range: -1.9483
Max Act: 1.3275. Min Act: -0.0001
Data Index: 1942813 (The Pile)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9483. Min Range: -1.9483
Max Act: 1.2963. Min Act: -0.0001
Data Index: 1155001 (The Pile)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9483. Min Range: -1.9483
Max Act: 1.2127. Min Act: -0.0001
Data Index: 1358354 (The Pile)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9483. Min Range: -1.9483
Max Act: 1.2251. Min Act: -0.0001
Data Index: 94321 (The Pile)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9483. Min Range: -1.9483
Max Act: 1.3031. Min Act: -0.0001
Data Index: 1169265 (The Pile)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9483. Min Range: -1.9483
Max Act: 1.2349. Min Act: -0.0001
Data Index: 87988 (The Pile)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9483. Min Range: -1.9483
Max Act: 1.3036. Min Act: -0.0001
Data Index: 1613283 (The Pile)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9483. Min Range: -1.9483
Max Act: 1.2468. Min Act: -0.0001
Data Index: 44482 (The Pile)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9483. Min Range: -1.9483
Max Act: 1.2688. Min Act: -0.0001
Data Index: 1512238 (The Pile)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9483. Min Range: -1.9483
Max Act: 1.3380. Min Act: -0.0001
Data Index: 831228 (The Pile)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #19