Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1489 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.1258. Min Range: -2.1258
Max Act: 2.1258. Min Act: -0.0001
Data Index: 997618 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1258. Min Range: -2.1258
Max Act: 1.6683. Min Act: -0.0001
Data Index: 723461 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1258. Min Range: -2.1258
Max Act: 1.8097. Min Act: -0.0001
Data Index: 342613 (C4 (Web Text))
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1258. Min Range: -2.1258
Max Act: 1.8674. Min Act: -0.0001
Data Index: 644807 (C4 (Web Text))
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1258. Min Range: -2.1258
Max Act: 1.6919. Min Act: -0.0001
Data Index: 345144 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1258. Min Range: -2.1258
Max Act: 1.7766. Min Act: -0.0001
Data Index: 774692 (C4 (Web Text))
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1258. Min Range: -2.1258
Max Act: 1.7597. Min Act: -0.0001
Data Index: 1258910 (C4 (Web Text))
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1258. Min Range: -2.1258
Max Act: 1.7966. Min Act: -0.0001
Data Index: 638937 (C4 (Web Text))
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1258. Min Range: -2.1258
Max Act: 1.3548. Min Act: -0.0001
Data Index: 529196 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1258. Min Range: -2.1258
Max Act: 1.7566. Min Act: -0.0001
Data Index: 1185752 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1258. Min Range: -2.1258
Max Act: 1.6317. Min Act: -0.0001
Data Index: 290317 (C4 (Web Text))
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1258. Min Range: -2.1258
Max Act: 0.6607. Min Act: -0.0001
Data Index: 754464 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1258. Min Range: -2.1258
Max Act: 1.5408. Min Act: -0.0001
Data Index: 1116217 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1258. Min Range: -2.1258
Max Act: 1.5881. Min Act: -0.0001
Data Index: 1021664 (C4 (Web Text))
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1258. Min Range: -2.1258
Max Act: 1.5800. Min Act: -0.0001
Data Index: 19305 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1258. Min Range: -2.1258
Max Act: 1.4954. Min Act: -0.0001
Data Index: 1084024 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1258. Min Range: -2.1258
Max Act: 1.6005. Min Act: -0.0001
Data Index: 33650 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1258. Min Range: -2.1258
Max Act: 1.5043. Min Act: -0.0001
Data Index: 97930 (C4 (Web Text))
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1258. Min Range: -2.1258
Max Act: 1.5189. Min Act: -0.0001
Data Index: 532345 (C4 (Web Text))
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1258. Min Range: -2.1258
Max Act: 1.5893. Min Act: -0.0001
Data Index: 360680 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19