Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 604 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 4.4976. Min Range: -4.4976
Max Act: 4.4976. Min Act: -0.0001
Data Index: 882857 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4976. Min Range: -4.4976
Max Act: 4.3943. Min Act: -0.0001
Data Index: 196341 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4976. Min Range: -4.4976
Max Act: 4.4123. Min Act: -0.0001
Data Index: 283862 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4976. Min Range: -4.4976
Max Act: 4.0200. Min Act: -0.0001
Data Index: 270238 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4976. Min Range: -4.4976
Max Act: 4.1556. Min Act: -0.0001
Data Index: 1121929 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4976. Min Range: -4.4976
Max Act: 4.0146. Min Act: -0.0001
Data Index: 1356583 (C4 (Web Text))
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4976. Min Range: -4.4976
Max Act: 3.8596. Min Act: -0.0001
Data Index: 203479 (C4 (Web Text))
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4976. Min Range: -4.4976
Max Act: 3.5930. Min Act: -0.0001
Data Index: 488688 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4976. Min Range: -4.4976
Max Act: 3.6118. Min Act: -0.0001
Data Index: 694052 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4976. Min Range: -4.4976
Max Act: 3.5486. Min Act: -0.0001
Data Index: 1254240 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4976. Min Range: -4.4976
Max Act: 3.4727. Min Act: -0.0001
Data Index: 1257677 (C4 (Web Text))
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4976. Min Range: -4.4976
Max Act: 3.5841. Min Act: -0.0001
Data Index: 945071 (C4 (Web Text))
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4976. Min Range: -4.4976
Max Act: 3.5918. Min Act: -0.0001
Data Index: 690733 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4976. Min Range: -4.4976
Max Act: 3.2484. Min Act: -0.0001
Data Index: 1035774 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4976. Min Range: -4.4976
Max Act: 3.3861. Min Act: -0.0001
Data Index: 1210132 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4976. Min Range: -4.4976
Max Act: 3.3515. Min Act: -0.0001
Data Index: 13265 (C4 (Web Text))
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4976. Min Range: -4.4976
Max Act: 3.3294. Min Act: -0.0001
Data Index: 682242 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4976. Min Range: -4.4976
Max Act: 2.9301. Min Act: -0.0001
Data Index: 243556 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4976. Min Range: -4.4976
Max Act: 2.7661. Min Act: -0.0001
Data Index: 214565 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4976. Min Range: -4.4976
Max Act: 3.0701. Min Act: -0.0001
Data Index: 83802 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #19