Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 93 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 2.2201. Min Range: -2.2201
Max Act: 2.2201. Min Act: -0.0001
Data Index: 874271 (C4 (Web Text))
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2201. Min Range: -2.2201
Max Act: 1.6131. Min Act: -0.0001
Data Index: 1642918 (Python Code)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2201. Min Range: -2.2201
Max Act: 1.5863. Min Act: -0.0001
Data Index: 630886 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2201. Min Range: -2.2201
Max Act: 1.5533. Min Act: -0.0001
Data Index: 623006 (C4 (Web Text))
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2201. Min Range: -2.2201
Max Act: 1.3803. Min Act: -0.0001
Data Index: 1616284 (Python Code)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2201. Min Range: -2.2201
Max Act: 1.3215. Min Act: -0.0001
Data Index: 1625031 (Python Code)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2201. Min Range: -2.2201
Max Act: 1.3912. Min Act: -0.0001
Data Index: 1485405 (Python Code)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2201. Min Range: -2.2201
Max Act: 1.3299. Min Act: -0.0001
Data Index: 422361 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2201. Min Range: -2.2201
Max Act: 1.4071. Min Act: -0.0001
Data Index: 893680 (C4 (Web Text))
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2201. Min Range: -2.2201
Max Act: 1.5736. Min Act: -0.0001
Data Index: 426212 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2201. Min Range: -2.2201
Max Act: 1.1497. Min Act: -0.0001
Data Index: 32505 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2201. Min Range: -2.2201
Max Act: 1.2952. Min Act: -0.0001
Data Index: 1380449 (Python Code)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2201. Min Range: -2.2201
Max Act: 1.3085. Min Act: -0.0001
Data Index: 941635 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2201. Min Range: -2.2201
Max Act: 1.2459. Min Act: -0.0001
Data Index: 1396241 (Python Code)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2201. Min Range: -2.2201
Max Act: 1.2618. Min Act: -0.0001
Data Index: 609968 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2201. Min Range: -2.2201
Max Act: 1.2938. Min Act: -0.0001
Data Index: 1195447 (C4 (Web Text))
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2201. Min Range: -2.2201
Max Act: 1.3315. Min Act: -0.0001
Data Index: 538431 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2201. Min Range: -2.2201
Max Act: 1.3334. Min Act: -0.0001
Data Index: 1512402 (Python Code)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2201. Min Range: -2.2201
Max Act: 1.2471. Min Act: -0.0001
Data Index: 1254059 (C4 (Web Text))
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2201. Min Range: -2.2201
Max Act: 1.2554. Min Act: -0.0001
Data Index: 248240 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #19