Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2398 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 4.4622. Min Range: -4.4622
Max Act: 4.3924. Min Act: -0.0001
Data Index: 1632485 (Python Code)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4622. Min Range: -4.4622
Max Act: 4.4622. Min Act: -0.0001
Data Index: 1403239 (Python Code)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4622. Min Range: -4.4622
Max Act: 4.1930. Min Act: -0.0001
Data Index: 1646297 (Python Code)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4622. Min Range: -4.4622
Max Act: 4.1359. Min Act: -0.0001
Data Index: 1380282 (Python Code)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4622. Min Range: -4.4622
Max Act: 4.2462. Min Act: -0.0001
Data Index: 1566682 (Python Code)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4622. Min Range: -4.4622
Max Act: 4.4004. Min Act: -0.0001
Data Index: 1649089 (Python Code)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4622. Min Range: -4.4622
Max Act: 4.2100. Min Act: -0.0001
Data Index: 1437984 (Python Code)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4622. Min Range: -4.4622
Max Act: 4.2369. Min Act: -0.0001
Data Index: 1630446 (Python Code)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4622. Min Range: -4.4622
Max Act: 4.0468. Min Act: -0.0001
Data Index: 1563278 (Python Code)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4622. Min Range: -4.4622
Max Act: 4.2014. Min Act: -0.0001
Data Index: 1389220 (Python Code)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4622. Min Range: -4.4622
Max Act: 4.1833. Min Act: -0.0001
Data Index: 1457447 (Python Code)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4622. Min Range: -4.4622
Max Act: 4.0481. Min Act: -0.0001
Data Index: 1435785 (Python Code)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4622. Min Range: -4.4622
Max Act: 4.1782. Min Act: -0.0001
Data Index: 1597395 (Python Code)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4622. Min Range: -4.4622
Max Act: 4.0056. Min Act: -0.0001
Data Index: 1550745 (Python Code)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4622. Min Range: -4.4622
Max Act: 4.0238. Min Act: -0.0001
Data Index: 1374089 (Python Code)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4622. Min Range: -4.4622
Max Act: 4.1799. Min Act: -0.0001
Data Index: 1525254 (Python Code)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4622. Min Range: -4.4622
Max Act: 4.1527. Min Act: -0.0001
Data Index: 1525936 (Python Code)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4622. Min Range: -4.4622
Max Act: 4.1632. Min Act: -0.0001
Data Index: 1389791 (Python Code)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4622. Min Range: -4.4622
Max Act: 4.3064. Min Act: -0.0001
Data Index: 1621234 (Python Code)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4622. Min Range: -4.4622
Max Act: 4.1492. Min Act: -0.0001
Data Index: 1568521 (Python Code)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #19