Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1060 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.1278. Min Range: -1.1278
Max Act: 1.1278. Min Act: -0.0001
Data Index: 218759 (The Pile)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1278. Min Range: -1.1278
Max Act: 0.9468. Min Act: -0.0001
Data Index: 365936 (The Pile)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1278. Min Range: -1.1278
Max Act: 0.9221. Min Act: -0.0001
Data Index: 924001 (The Pile)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1278. Min Range: -1.1278
Max Act: 0.9771. Min Act: -0.0002
Data Index: 1724575 (The Pile)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1278. Min Range: -1.1278
Max Act: 0.9075. Min Act: -0.0001
Data Index: 1245064 (The Pile)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1278. Min Range: -1.1278
Max Act: 0.9520. Min Act: -0.0001
Data Index: 698144 (The Pile)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1278. Min Range: -1.1278
Max Act: 0.8841. Min Act: -0.0001
Data Index: 1656921 (The Pile)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1278. Min Range: -1.1278
Max Act: 0.9760. Min Act: -0.0001
Data Index: 1357705 (The Pile)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1278. Min Range: -1.1278
Max Act: 0.9032. Min Act: -0.0001
Data Index: 1131080 (The Pile)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1278. Min Range: -1.1278
Max Act: 0.8953. Min Act: -0.0001
Data Index: 777517 (The Pile)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1278. Min Range: -1.1278
Max Act: 0.8803. Min Act: -0.0001
Data Index: 903165 (The Pile)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1278. Min Range: -1.1278
Max Act: 0.8619. Min Act: -0.0001
Data Index: 1190753 (The Pile)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1278. Min Range: -1.1278
Max Act: 0.8786. Min Act: -0.0001
Data Index: 1966415 (The Pile)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1278. Min Range: -1.1278
Max Act: 0.9457. Min Act: -0.0001
Data Index: 426522 (The Pile)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1278. Min Range: -1.1278
Max Act: 0.8659. Min Act: -0.0001
Data Index: 1118224 (The Pile)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1278. Min Range: -1.1278
Max Act: 0.9266. Min Act: -0.0001
Data Index: 362926 (The Pile)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1278. Min Range: -1.1278
Max Act: 0.9479. Min Act: -0.0001
Data Index: 630660 (The Pile)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1278. Min Range: -1.1278
Max Act: 0.8434. Min Act: -0.0001
Data Index: 174059 (The Pile)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1278. Min Range: -1.1278
Max Act: 0.8408. Min Act: -0.0001
Data Index: 1876096 (The Pile)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1278. Min Range: -1.1278
Max Act: 0.8368. Min Act: -0.0001
Data Index: 1792875 (The Pile)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #19