Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 987 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.5684. Min Range: -0.5684
Max Act: 0.5684. Min Act: -0.0001
Data Index: 391147 (The Pile)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5684. Min Range: -0.5684
Max Act: 0.5059. Min Act: -0.0001
Data Index: 477537 (The Pile)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5684. Min Range: -0.5684
Max Act: 0.5439. Min Act: -0.0001
Data Index: 1122436 (The Pile)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5684. Min Range: -0.5684
Max Act: 0.4506. Min Act: -0.0001
Data Index: 1527471 (The Pile)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5684. Min Range: -0.5684
Max Act: 0.4646. Min Act: -0.0001
Data Index: 878257 (The Pile)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5684. Min Range: -0.5684
Max Act: 0.4468. Min Act: -0.0001
Data Index: 260732 (The Pile)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5684. Min Range: -0.5684
Max Act: 0.4471. Min Act: -0.0001
Data Index: 1072836 (The Pile)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5684. Min Range: -0.5684
Max Act: 0.4464. Min Act: -0.0001
Data Index: 1106130 (The Pile)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5684. Min Range: -0.5684
Max Act: 0.4276. Min Act: -0.0001
Data Index: 1505851 (The Pile)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5684. Min Range: -0.5684
Max Act: 0.4455. Min Act: -0.0001
Data Index: 732125 (The Pile)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5684. Min Range: -0.5684
Max Act: 0.4400. Min Act: -0.0001
Data Index: 1479607 (The Pile)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5684. Min Range: -0.5684
Max Act: 0.4221. Min Act: -0.0001
Data Index: 143047 (The Pile)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5684. Min Range: -0.5684
Max Act: 0.4460. Min Act: -0.0001
Data Index: 27454 (The Pile)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5684. Min Range: -0.5684
Max Act: 0.4067. Min Act: -0.0001
Data Index: 757399 (The Pile)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5684. Min Range: -0.5684
Max Act: 0.4152. Min Act: -0.0001
Data Index: 153185 (The Pile)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5684. Min Range: -0.5684
Max Act: 0.4118. Min Act: -0.0001
Data Index: 553942 (The Pile)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5684. Min Range: -0.5684
Max Act: 0.4113. Min Act: -0.0001
Data Index: 794614 (The Pile)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5684. Min Range: -0.5684
Max Act: 0.4107. Min Act: -0.0001
Data Index: 647131 (The Pile)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5684. Min Range: -0.5684
Max Act: 0.4088. Min Act: -0.0001
Data Index: 263305 (The Pile)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5684. Min Range: -0.5684
Max Act: 0.4121. Min Act: -0.0001
Data Index: 1789149 (The Pile)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19