Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1041 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.2867. Min Range: -1.2867
Max Act: 1.2867. Min Act: -0.0001
Data Index: 1392486 (The Pile)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2867. Min Range: -1.2867
Max Act: 1.0774. Min Act: -0.0001
Data Index: 842861 (The Pile)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2867. Min Range: -1.2867
Max Act: 1.0301. Min Act: -0.0001
Data Index: 1606404 (The Pile)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2867. Min Range: -1.2867
Max Act: 0.9972. Min Act: -0.0001
Data Index: 335361 (The Pile)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2867. Min Range: -1.2867
Max Act: 0.9870. Min Act: -0.0001
Data Index: 1067303 (The Pile)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2867. Min Range: -1.2867
Max Act: 0.9875. Min Act: -0.0001
Data Index: 238705 (The Pile)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2867. Min Range: -1.2867
Max Act: 0.9536. Min Act: -0.0001
Data Index: 592150 (The Pile)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2867. Min Range: -1.2867
Max Act: 0.9604. Min Act: -0.0001
Data Index: 993274 (The Pile)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2867. Min Range: -1.2867
Max Act: 0.8721. Min Act: -0.0001
Data Index: 828984 (The Pile)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2867. Min Range: -1.2867
Max Act: 0.9393. Min Act: -0.0001
Data Index: 443970 (The Pile)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2867. Min Range: -1.2867
Max Act: 0.9629. Min Act: -0.0001
Data Index: 364162 (The Pile)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2867. Min Range: -1.2867
Max Act: 0.9158. Min Act: -0.0001
Data Index: 1153391 (The Pile)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2867. Min Range: -1.2867
Max Act: 0.9362. Min Act: -0.0001
Data Index: 891274 (The Pile)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2867. Min Range: -1.2867
Max Act: 0.9489. Min Act: -0.0001
Data Index: 568288 (The Pile)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2867. Min Range: -1.2867
Max Act: 0.9374. Min Act: -0.0001
Data Index: 1243014 (The Pile)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2867. Min Range: -1.2867
Max Act: 0.9319. Min Act: -0.0001
Data Index: 309326 (The Pile)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2867. Min Range: -1.2867
Max Act: 0.9009. Min Act: -0.0001
Data Index: 429814 (The Pile)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2867. Min Range: -1.2867
Max Act: 0.8877. Min Act: -0.0001
Data Index: 873371 (The Pile)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2867. Min Range: -1.2867
Max Act: 0.8798. Min Act: -0.0001
Data Index: 1043584 (The Pile)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2867. Min Range: -1.2867
Max Act: 0.8588. Min Act: -0.0001
Data Index: 705541 (The Pile)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #19