Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1675 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.2008. Min Range: -2.2008
Max Act: 2.2008. Min Act: -0.0001
Data Index: 1439396 (Python Code)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2008. Min Range: -2.2008
Max Act: 1.5750. Min Act: -0.0001
Data Index: 1527182 (Python Code)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2008. Min Range: -2.2008
Max Act: 1.3278. Min Act: -0.0001
Data Index: 1604492 (Python Code)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2008. Min Range: -2.2008
Max Act: 1.4144. Min Act: -0.0001
Data Index: 1562219 (Python Code)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2008. Min Range: -2.2008
Max Act: 1.4073. Min Act: -0.0001
Data Index: 1586199 (Python Code)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2008. Min Range: -2.2008
Max Act: 1.3842. Min Act: -0.0001
Data Index: 1619068 (Python Code)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2008. Min Range: -2.2008
Max Act: 1.4337. Min Act: -0.0001
Data Index: 1443877 (Python Code)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2008. Min Range: -2.2008
Max Act: 1.3960. Min Act: -0.0001
Data Index: 1458370 (Python Code)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2008. Min Range: -2.2008
Max Act: 1.4668. Min Act: -0.0001
Data Index: 1509401 (Python Code)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2008. Min Range: -2.2008
Max Act: 1.4350. Min Act: -0.0001
Data Index: 1645491 (Python Code)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2008. Min Range: -2.2008
Max Act: 1.3393. Min Act: -0.0001
Data Index: 1535470 (Python Code)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2008. Min Range: -2.2008
Max Act: 1.3580. Min Act: -0.0001
Data Index: 1439883 (Python Code)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2008. Min Range: -2.2008
Max Act: 1.3187. Min Act: -0.0001
Data Index: 1578668 (Python Code)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2008. Min Range: -2.2008
Max Act: 1.3048. Min Act: -0.0001
Data Index: 1641957 (Python Code)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2008. Min Range: -2.2008
Max Act: 1.2871. Min Act: -0.0001
Data Index: 1430784 (Python Code)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2008. Min Range: -2.2008
Max Act: 1.2872. Min Act: -0.0001
Data Index: 1453862 (Python Code)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2008. Min Range: -2.2008
Max Act: 1.3371. Min Act: -0.0001
Data Index: 1453540 (Python Code)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2008. Min Range: -2.2008
Max Act: 1.2642. Min Act: -0.0001
Data Index: 1520899 (Python Code)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2008. Min Range: -2.2008
Max Act: 1.2145. Min Act: -0.0001
Data Index: 1586042 (Python Code)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2008. Min Range: -2.2008
Max Act: 1.2063. Min Act: -0.0001
Data Index: 1407278 (Python Code)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #19