Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 922 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.8135. Min Range: -1.8135
Max Act: 1.8135. Min Act: -0.0000
Data Index: 1841325 (The Pile)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8135. Min Range: -1.8135
Max Act: 1.5222. Min Act: -0.0001
Data Index: 484511 (The Pile)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8135. Min Range: -1.8135
Max Act: 1.5436. Min Act: -0.0000
Data Index: 1896021 (The Pile)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8135. Min Range: -1.8135
Max Act: 1.4413. Min Act: -0.0000
Data Index: 544996 (The Pile)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8135. Min Range: -1.8135
Max Act: 1.4582. Min Act: -0.0000
Data Index: 988635 (The Pile)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8135. Min Range: -1.8135
Max Act: 1.3844. Min Act: -0.0000
Data Index: 345628 (The Pile)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8135. Min Range: -1.8135
Max Act: 1.4118. Min Act: -0.0000
Data Index: 1940394 (The Pile)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8135. Min Range: -1.8135
Max Act: 1.3924. Min Act: -0.0000
Data Index: 431549 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8135. Min Range: -1.8135
Max Act: 1.3794. Min Act: -0.0000
Data Index: 1857684 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8135. Min Range: -1.8135
Max Act: 1.2749. Min Act: -0.0000
Data Index: 503355 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8135. Min Range: -1.8135
Max Act: 1.3441. Min Act: -0.0000
Data Index: 1103881 (The Pile)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8135. Min Range: -1.8135
Max Act: 1.4203. Min Act: -0.0000
Data Index: 882764 (The Pile)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8135. Min Range: -1.8135
Max Act: 1.3648. Min Act: -0.0000
Data Index: 1948777 (The Pile)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8135. Min Range: -1.8135
Max Act: 1.3288. Min Act: -0.0000
Data Index: 80606 (The Pile)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8135. Min Range: -1.8135
Max Act: 1.2775. Min Act: -0.0000
Data Index: 1230283 (The Pile)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8135. Min Range: -1.8135
Max Act: 1.4592. Min Act: -0.0001
Data Index: 1626193 (The Pile)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8135. Min Range: -1.8135
Max Act: 1.2928. Min Act: -0.0001
Data Index: 508906 (The Pile)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8135. Min Range: -1.8135
Max Act: 1.3171. Min Act: -0.0000
Data Index: 1475089 (The Pile)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8135. Min Range: -1.8135
Max Act: 1.4000. Min Act: -0.0001
Data Index: 1027541 (The Pile)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8135. Min Range: -1.8135
Max Act: 1.3540. Min Act: -0.0000
Data Index: 1592214 (The Pile)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19