Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1748 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.6221. Min Range: -0.6221
Max Act: 0.6221. Min Act: -0.0001
Data Index: 1378709 (Python Code)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6221. Min Range: -0.6221
Max Act: 0.5685. Min Act: -0.0001
Data Index: 1443612 (Python Code)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6221. Min Range: -0.6221
Max Act: 0.5000. Min Act: -0.0001
Data Index: 1219229 (C4 (Web Text))
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6221. Min Range: -0.6221
Max Act: 0.4917. Min Act: -0.0001
Data Index: 1232344 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6221. Min Range: -0.6221
Max Act: 0.4937. Min Act: -0.0001
Data Index: 1368722 (Python Code)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6221. Min Range: -0.6221
Max Act: 0.4804. Min Act: -0.0001
Data Index: 1295179 (C4 (Web Text))
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6221. Min Range: -0.6221
Max Act: 0.4855. Min Act: -0.0001
Data Index: 1478768 (Python Code)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6221. Min Range: -0.6221
Max Act: 0.5177. Min Act: -0.0001
Data Index: 1624166 (Python Code)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6221. Min Range: -0.6221
Max Act: 0.4762. Min Act: -0.0001
Data Index: 496080 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6221. Min Range: -0.6221
Max Act: 0.4414. Min Act: -0.0001
Data Index: 199711 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6221. Min Range: -0.6221
Max Act: 0.4763. Min Act: -0.0001
Data Index: 582743 (C4 (Web Text))
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6221. Min Range: -0.6221
Max Act: 0.4738. Min Act: -0.0001
Data Index: 203296 (C4 (Web Text))
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6221. Min Range: -0.6221
Max Act: 0.4397. Min Act: -0.0001
Data Index: 474497 (C4 (Web Text))
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6221. Min Range: -0.6221
Max Act: 0.4713. Min Act: -0.0001
Data Index: 1629780 (Python Code)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6221. Min Range: -0.6221
Max Act: 0.4555. Min Act: -0.0001
Data Index: 22517 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6221. Min Range: -0.6221
Max Act: 0.4581. Min Act: -0.0001
Data Index: 1126207 (C4 (Web Text))
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6221. Min Range: -0.6221
Max Act: 0.4563. Min Act: -0.0001
Data Index: 1633844 (Python Code)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6221. Min Range: -0.6221
Max Act: 0.4532. Min Act: -0.0001
Data Index: 1374649 (Python Code)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6221. Min Range: -0.6221
Max Act: 0.4254. Min Act: -0.0001
Data Index: 1595455 (Python Code)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6221. Min Range: -0.6221
Max Act: 0.4548. Min Act: -0.0001
Data Index: 1285618 (C4 (Web Text))
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19