Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 24 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.5174. Min Range: -1.5174
Max Act: 1.5174. Min Act: -0.0001
Data Index: 1585375 (The Pile)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5174. Min Range: -1.5174
Max Act: 1.3643. Min Act: -0.0001
Data Index: 650096 (The Pile)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5174. Min Range: -1.5174
Max Act: 1.0750. Min Act: -0.0001
Data Index: 1722398 (The Pile)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5174. Min Range: -1.5174
Max Act: 1.1688. Min Act: -0.0001
Data Index: 1065936 (The Pile)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5174. Min Range: -1.5174
Max Act: 1.1051. Min Act: -0.0000
Data Index: 1610590 (The Pile)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5174. Min Range: -1.5174
Max Act: 1.0770. Min Act: -0.0001
Data Index: 1450679 (The Pile)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5174. Min Range: -1.5174
Max Act: 1.1546. Min Act: -0.0001
Data Index: 38786 (The Pile)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5174. Min Range: -1.5174
Max Act: 1.0099. Min Act: -0.0001
Data Index: 162266 (The Pile)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5174. Min Range: -1.5174
Max Act: 0.9734. Min Act: -0.0001
Data Index: 797277 (The Pile)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5174. Min Range: -1.5174
Max Act: 0.9857. Min Act: -0.0001
Data Index: 422133 (The Pile)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5174. Min Range: -1.5174
Max Act: 0.9566. Min Act: -0.0001
Data Index: 837543 (The Pile)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5174. Min Range: -1.5174
Max Act: 1.0057. Min Act: -0.0001
Data Index: 768126 (The Pile)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5174. Min Range: -1.5174
Max Act: 0.8884. Min Act: -0.0001
Data Index: 837159 (The Pile)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5174. Min Range: -1.5174
Max Act: 0.9282. Min Act: -0.0001
Data Index: 1655993 (The Pile)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5174. Min Range: -1.5174
Max Act: 0.9208. Min Act: -0.0001
Data Index: 883588 (The Pile)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5174. Min Range: -1.5174
Max Act: 0.9268. Min Act: -0.0001
Data Index: 1554134 (The Pile)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5174. Min Range: -1.5174
Max Act: 0.9146. Min Act: -0.0001
Data Index: 114389 (The Pile)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5174. Min Range: -1.5174
Max Act: 0.9151. Min Act: -0.0001
Data Index: 1646839 (The Pile)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5174. Min Range: -1.5174
Max Act: 0.9486. Min Act: -0.0001
Data Index: 87994 (The Pile)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5174. Min Range: -1.5174
Max Act: 0.9189. Min Act: -0.0001
Data Index: 1036962 (The Pile)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19