Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 578 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.4873. Min Range: -0.4873
Max Act: 0.4392. Min Act: -0.0001
Data Index: 416038 (C4 (Web Text))
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4873. Min Range: -0.4873
Max Act: 0.4387. Min Act: -0.0001
Data Index: 471777 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4873. Min Range: -0.4873
Max Act: 0.4873. Min Act: -0.0001
Data Index: 192428 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4873. Min Range: -0.4873
Max Act: 0.4327. Min Act: -0.0001
Data Index: 66990 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4873. Min Range: -0.4873
Max Act: 0.4125. Min Act: -0.0001
Data Index: 86575 (C4 (Web Text))
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4873. Min Range: -0.4873
Max Act: 0.4026. Min Act: -0.0001
Data Index: 342075 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4873. Min Range: -0.4873
Max Act: 0.3698. Min Act: -0.0001
Data Index: 196228 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4873. Min Range: -0.4873
Max Act: 0.3979. Min Act: -0.0001
Data Index: 917120 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4873. Min Range: -0.4873
Max Act: 0.4136. Min Act: -0.0001
Data Index: 1317425 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4873. Min Range: -0.4873
Max Act: 0.4103. Min Act: -0.0001
Data Index: 1089449 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4873. Min Range: -0.4873
Max Act: 0.4074. Min Act: -0.0001
Data Index: 847406 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4873. Min Range: -0.4873
Max Act: 0.3856. Min Act: -0.0001
Data Index: 470079 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4873. Min Range: -0.4873
Max Act: 0.3961. Min Act: -0.0001
Data Index: 1175846 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4873. Min Range: -0.4873
Max Act: 0.3960. Min Act: -0.0001
Data Index: 1004315 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4873. Min Range: -0.4873
Max Act: 0.3946. Min Act: -0.0001
Data Index: 614936 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4873. Min Range: -0.4873
Max Act: 0.3978. Min Act: -0.0001
Data Index: 932553 (C4 (Web Text))
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4873. Min Range: -0.4873
Max Act: 0.3905. Min Act: -0.0001
Data Index: 321408 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4873. Min Range: -0.4873
Max Act: 0.3854. Min Act: -0.0001
Data Index: 122960 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4873. Min Range: -0.4873
Max Act: 0.3874. Min Act: -0.0001
Data Index: 369568 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4873. Min Range: -0.4873
Max Act: 0.3860. Min Act: -0.0001
Data Index: 578014 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19