Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 2667 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.2097. Min Range: -1.2097
Max Act: 1.2097. Min Act: -0.0001
Data Index: 433876 (The Pile)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2097. Min Range: -1.2097
Max Act: 1.1269. Min Act: -0.0001
Data Index: 1681978 (The Pile)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2097. Min Range: -1.2097
Max Act: 1.0591. Min Act: -0.0001
Data Index: 1064226 (The Pile)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2097. Min Range: -1.2097
Max Act: 1.1275. Min Act: -0.0001
Data Index: 117844 (The Pile)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2097. Min Range: -1.2097
Max Act: 1.0117. Min Act: -0.0001
Data Index: 376978 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2097. Min Range: -1.2097
Max Act: 1.0486. Min Act: -0.0001
Data Index: 1477090 (The Pile)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2097. Min Range: -1.2097
Max Act: 0.8803. Min Act: -0.0001
Data Index: 1291555 (The Pile)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2097. Min Range: -1.2097
Max Act: 1.0083. Min Act: -0.0001
Data Index: 334843 (The Pile)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2097. Min Range: -1.2097
Max Act: 0.8802. Min Act: -0.0001
Data Index: 1211498 (The Pile)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2097. Min Range: -1.2097
Max Act: 0.8401. Min Act: -0.0001
Data Index: 486489 (The Pile)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2097. Min Range: -1.2097
Max Act: 0.9149. Min Act: -0.0001
Data Index: 1934980 (The Pile)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2097. Min Range: -1.2097
Max Act: 0.8377. Min Act: -0.0001
Data Index: 1735513 (The Pile)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2097. Min Range: -1.2097
Max Act: 0.8583. Min Act: -0.0001
Data Index: 1585032 (The Pile)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2097. Min Range: -1.2097
Max Act: 0.9733. Min Act: -0.0001
Data Index: 707602 (The Pile)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2097. Min Range: -1.2097
Max Act: 0.8761. Min Act: -0.0001
Data Index: 1113812 (The Pile)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2097. Min Range: -1.2097
Max Act: 0.8755. Min Act: -0.0001
Data Index: 1718593 (The Pile)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2097. Min Range: -1.2097
Max Act: 0.7917. Min Act: -0.0001
Data Index: 1317987 (The Pile)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2097. Min Range: -1.2097
Max Act: 0.8905. Min Act: -0.0001
Data Index: 1038028 (The Pile)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2097. Min Range: -1.2097
Max Act: 0.8617. Min Act: -0.0001
Data Index: 283123 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2097. Min Range: -1.2097
Max Act: 0.8841. Min Act: -0.0001
Data Index: 1220608 (The Pile)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19