Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1178 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.4003. Min Range: -0.4003
Max Act: 0.3908. Min Act: -0.0001
Data Index: 1928429 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4003. Min Range: -0.4003
Max Act: 0.3940. Min Act: -0.0001
Data Index: 29641 (The Pile)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4003. Min Range: -0.4003
Max Act: 0.4003. Min Act: -0.0001
Data Index: 1897121 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4003. Min Range: -0.4003
Max Act: 0.3566. Min Act: -0.0001
Data Index: 790800 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4003. Min Range: -0.4003
Max Act: 0.3655. Min Act: -0.0001
Data Index: 1042547 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4003. Min Range: -0.4003
Max Act: 0.3473. Min Act: -0.0001
Data Index: 806244 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4003. Min Range: -0.4003
Max Act: 0.3447. Min Act: -0.0001
Data Index: 521719 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4003. Min Range: -0.4003
Max Act: 0.3398. Min Act: -0.0001
Data Index: 1930534 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4003. Min Range: -0.4003
Max Act: 0.3304. Min Act: -0.0001
Data Index: 1271148 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4003. Min Range: -0.4003
Max Act: 0.3151. Min Act: -0.0001
Data Index: 368213 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4003. Min Range: -0.4003
Max Act: 0.3249. Min Act: -0.0001
Data Index: 608080 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4003. Min Range: -0.4003
Max Act: 0.3390. Min Act: -0.0001
Data Index: 667542 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4003. Min Range: -0.4003
Max Act: 0.3448. Min Act: -0.0001
Data Index: 40589 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4003. Min Range: -0.4003
Max Act: 0.3258. Min Act: -0.0001
Data Index: 1294929 (The Pile)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4003. Min Range: -0.4003
Max Act: 0.3306. Min Act: -0.0001
Data Index: 957846 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4003. Min Range: -0.4003
Max Act: 0.3159. Min Act: -0.0001
Data Index: 686813 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4003. Min Range: -0.4003
Max Act: 0.3095. Min Act: -0.0001
Data Index: 341518 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4003. Min Range: -0.4003
Max Act: 0.3009. Min Act: -0.0001
Data Index: 1622278 (The Pile)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4003. Min Range: -0.4003
Max Act: 0.3163. Min Act: -0.0001
Data Index: 1003574 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4003. Min Range: -0.4003
Max Act: 0.3199. Min Act: -0.0001
Data Index: 294418 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19