Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1724 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.7781. Min Act: -0.0001
Data Index: 239793 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.8153. Min Act: -0.0001
Data Index: 170519 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.7532. Min Act: -0.0001
Data Index: 1102663 (C4 (Web Text))
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.7069. Min Act: -0.0001
Data Index: 689733 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.7256. Min Act: -0.0001
Data Index: 767234 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.6876. Min Act: -0.0001
Data Index: 174415 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.7005. Min Act: -0.0001
Data Index: 1035774 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.6736. Min Act: -0.0001
Data Index: 880109 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.6805. Min Act: -0.0001
Data Index: 912642 (C4 (Web Text))
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.6530. Min Act: -0.0001
Data Index: 1072918 (C4 (Web Text))
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.6448. Min Act: -0.0001
Data Index: 745070 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.6607. Min Act: -0.0001
Data Index: 988521 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.6582. Min Act: -0.0001
Data Index: 928069 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.5728. Min Act: -0.0001
Data Index: 800792 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.6545. Min Act: -0.0001
Data Index: 703368 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.6708. Min Act: -0.0001
Data Index: 721989 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.6495. Min Act: -0.0001
Data Index: 506528 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.6638. Min Act: -0.0001
Data Index: 183146 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.6405. Min Act: -0.0001
Data Index: 529696 (C4 (Web Text))
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8153. Min Range: -0.8153
Max Act: 0.6183. Min Act: -0.0001
Data Index: 913094 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19