Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4169 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.3044. Min Range: -2.3044
Max Act: 2.3044. Min Act: -0.0001
Data Index: 450573 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3044. Min Range: -2.3044
Max Act: 2.0852. Min Act: -0.0001
Data Index: 1290529 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3044. Min Range: -2.3044
Max Act: 2.0319. Min Act: -0.0001
Data Index: 649452 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3044. Min Range: -2.3044
Max Act: 2.0344. Min Act: -0.0001
Data Index: 433436 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3044. Min Range: -2.3044
Max Act: 2.0031. Min Act: -0.0001
Data Index: 135034 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3044. Min Range: -2.3044
Max Act: 1.9903. Min Act: -0.0001
Data Index: 1093927 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3044. Min Range: -2.3044
Max Act: 1.7932. Min Act: -0.0001
Data Index: 679541 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3044. Min Range: -2.3044
Max Act: 1.8074. Min Act: -0.0001
Data Index: 1202847 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3044. Min Range: -2.3044
Max Act: 1.8045. Min Act: -0.0001
Data Index: 194000 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3044. Min Range: -2.3044
Max Act: 1.8052. Min Act: -0.0001
Data Index: 207707 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3044. Min Range: -2.3044
Max Act: 1.7727. Min Act: -0.0001
Data Index: 293559 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3044. Min Range: -2.3044
Max Act: 1.6683. Min Act: -0.0001
Data Index: 209951 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3044. Min Range: -2.3044
Max Act: 1.5842. Min Act: -0.0001
Data Index: 407499 (C4 (Web Text))
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3044. Min Range: -2.3044
Max Act: 1.5469. Min Act: -0.0001
Data Index: 905671 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3044. Min Range: -2.3044
Max Act: 1.7186. Min Act: -0.0001
Data Index: 1174244 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3044. Min Range: -2.3044
Max Act: 1.7147. Min Act: -0.0001
Data Index: 345152 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3044. Min Range: -2.3044
Max Act: 1.4367. Min Act: -0.0001
Data Index: 706750 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3044. Min Range: -2.3044
Max Act: 1.3988. Min Act: -0.0001
Data Index: 964026 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3044. Min Range: -2.3044
Max Act: 1.4824. Min Act: -0.0001
Data Index: 374490 (C4 (Web Text))
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3044. Min Range: -2.3044
Max Act: 1.3147. Min Act: -0.0001
Data Index: 751189 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19