Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 3722 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 3.2295. Min Range: -3.2295
Max Act: 3.2295. Min Act: -0.0001
Data Index: 77282 (The Pile)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2295. Min Range: -3.2295
Max Act: 2.9740. Min Act: -0.0001
Data Index: 1249402 (The Pile)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2295. Min Range: -3.2295
Max Act: 3.1309. Min Act: -0.0001
Data Index: 388887 (The Pile)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2295. Min Range: -3.2295
Max Act: 3.0526. Min Act: -0.0001
Data Index: 16347 (The Pile)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2295. Min Range: -3.2295
Max Act: 2.7842. Min Act: -0.0001
Data Index: 357387 (The Pile)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2295. Min Range: -3.2295
Max Act: 3.0380. Min Act: -0.0001
Data Index: 1906883 (The Pile)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2295. Min Range: -3.2295
Max Act: 3.0029. Min Act: -0.0001
Data Index: 947722 (The Pile)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2295. Min Range: -3.2295
Max Act: 2.8244. Min Act: -0.0001
Data Index: 1372425 (The Pile)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2295. Min Range: -3.2295
Max Act: 2.9800. Min Act: -0.0001
Data Index: 1816421 (The Pile)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2295. Min Range: -3.2295
Max Act: 2.9885. Min Act: -0.0001
Data Index: 1831851 (The Pile)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2295. Min Range: -3.2295
Max Act: 2.9464. Min Act: -0.0001
Data Index: 1507835 (The Pile)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2295. Min Range: -3.2295
Max Act: 2.9167. Min Act: -0.0001
Data Index: 1607765 (The Pile)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2295. Min Range: -3.2295
Max Act: 2.8975. Min Act: -0.0001
Data Index: 820981 (The Pile)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2295. Min Range: -3.2295
Max Act: 2.8769. Min Act: -0.0001
Data Index: 397771 (The Pile)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2295. Min Range: -3.2295
Max Act: 2.7552. Min Act: -0.0001
Data Index: 65837 (The Pile)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2295. Min Range: -3.2295
Max Act: 2.5837. Min Act: -0.0001
Data Index: 1918844 (The Pile)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2295. Min Range: -3.2295
Max Act: 2.8314. Min Act: -0.0001
Data Index: 449239 (The Pile)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2295. Min Range: -3.2295
Max Act: 2.9556. Min Act: -0.0001
Data Index: 1245541 (The Pile)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2295. Min Range: -3.2295
Max Act: 2.8563. Min Act: -0.0001
Data Index: 1607990 (The Pile)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2295. Min Range: -3.2295
Max Act: 2.7793. Min Act: -0.0001
Data Index: 766140 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19