Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3083 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 3.0815. Min Range: -3.0815
Max Act: 3.0815. Min Act: -0.0001
Data Index: 1613014 (Python Code)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0815. Min Range: -3.0815
Max Act: 2.3652. Min Act: -0.0001
Data Index: 999907 (C4 (Web Text))
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0815. Min Range: -3.0815
Max Act: 2.6022. Min Act: -0.0001
Data Index: 1380853 (Python Code)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0815. Min Range: -3.0815
Max Act: 2.4547. Min Act: -0.0001
Data Index: 1587515 (Python Code)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0815. Min Range: -3.0815
Max Act: 2.4391. Min Act: -0.0001
Data Index: 1536108 (Python Code)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0815. Min Range: -3.0815
Max Act: 2.1978. Min Act: -0.0001
Data Index: 1657037 (Python Code)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0815. Min Range: -3.0815
Max Act: 2.4142. Min Act: -0.0001
Data Index: 963340 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0815. Min Range: -3.0815
Max Act: 2.3956. Min Act: -0.0001
Data Index: 1551356 (Python Code)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0815. Min Range: -3.0815
Max Act: 2.2386. Min Act: -0.0001
Data Index: 1526739 (Python Code)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0815. Min Range: -3.0815
Max Act: 2.0190. Min Act: -0.0001
Data Index: 1570513 (Python Code)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0815. Min Range: -3.0815
Max Act: 2.4210. Min Act: -0.0001
Data Index: 1446439 (Python Code)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0815. Min Range: -3.0815
Max Act: 2.3175. Min Act: -0.0000
Data Index: 1478100 (Python Code)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0815. Min Range: -3.0815
Max Act: 2.2826. Min Act: -0.0001
Data Index: 1484056 (Python Code)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0815. Min Range: -3.0815
Max Act: 2.1520. Min Act: -0.0001
Data Index: 1368753 (Python Code)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0815. Min Range: -3.0815
Max Act: 2.2490. Min Act: -0.0001
Data Index: 1619240 (Python Code)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0815. Min Range: -3.0815
Max Act: 2.1230. Min Act: -0.0001
Data Index: 1620413 (Python Code)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0815. Min Range: -3.0815
Max Act: 2.1228. Min Act: -0.0001
Data Index: 1390996 (Python Code)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0815. Min Range: -3.0815
Max Act: 2.3144. Min Act: -0.0001
Data Index: 1470433 (Python Code)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0815. Min Range: -3.0815
Max Act: 2.1147. Min Act: -0.0001
Data Index: 1488681 (Python Code)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0815. Min Range: -3.0815
Max Act: 2.0790. Min Act: -0.0001
Data Index: 1637184 (Python Code)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #19