Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3133 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.8909. Min Range: -2.8909
Max Act: 2.8909. Min Act: -0.0001
Data Index: 1399774 (Python Code)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8909. Min Range: -2.8909
Max Act: 2.8615. Min Act: -0.0001
Data Index: 1580527 (Python Code)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8909. Min Range: -2.8909
Max Act: 2.8321. Min Act: -0.0001
Data Index: 1456018 (Python Code)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8909. Min Range: -2.8909
Max Act: 2.5087. Min Act: -0.0001
Data Index: 1520147 (Python Code)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8909. Min Range: -2.8909
Max Act: 2.6961. Min Act: -0.0001
Data Index: 1598114 (Python Code)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8909. Min Range: -2.8909
Max Act: 2.5079. Min Act: -0.0001
Data Index: 1622049 (Python Code)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8909. Min Range: -2.8909
Max Act: 2.4624. Min Act: -0.0001
Data Index: 1532847 (Python Code)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8909. Min Range: -2.8909
Max Act: 2.4521. Min Act: -0.0000
Data Index: 1378944 (Python Code)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8909. Min Range: -2.8909
Max Act: 2.4467. Min Act: -0.0001
Data Index: 1511471 (Python Code)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8909. Min Range: -2.8909
Max Act: 2.4223. Min Act: -0.0001
Data Index: 214595 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8909. Min Range: -2.8909
Max Act: 2.4091. Min Act: -0.0001
Data Index: 482090 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8909. Min Range: -2.8909
Max Act: 2.2852. Min Act: -0.0001
Data Index: 1541115 (Python Code)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8909. Min Range: -2.8909
Max Act: 2.3742. Min Act: -0.0001
Data Index: 1387818 (Python Code)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8909. Min Range: -2.8909
Max Act: 2.5580. Min Act: -0.0001
Data Index: 1599897 (Python Code)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8909. Min Range: -2.8909
Max Act: 2.4140. Min Act: -0.0001
Data Index: 1550345 (Python Code)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8909. Min Range: -2.8909
Max Act: 2.1788. Min Act: -0.0000
Data Index: 1572461 (Python Code)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8909. Min Range: -2.8909
Max Act: 2.2068. Min Act: -0.0001
Data Index: 1650781 (Python Code)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8909. Min Range: -2.8909
Max Act: 2.2964. Min Act: -0.0001
Data Index: 1628496 (Python Code)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8909. Min Range: -2.8909
Max Act: 2.1791. Min Act: -0.0001
Data Index: 1607338 (Python Code)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8909. Min Range: -2.8909
Max Act: 2.2903. Min Act: -0.0000
Data Index: 1556548 (Python Code)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19