Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2322 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.2994. Min Range: -2.2994
Max Act: 2.2994. Min Act: -0.0001
Data Index: 1439977 (Python Code)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2994. Min Range: -2.2994
Max Act: 2.1746. Min Act: -0.0001
Data Index: 1555018 (Python Code)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2994. Min Range: -2.2994
Max Act: 2.0341. Min Act: -0.0001
Data Index: 1589072 (Python Code)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2994. Min Range: -2.2994
Max Act: 2.0337. Min Act: -0.0001
Data Index: 1485696 (Python Code)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2994. Min Range: -2.2994
Max Act: 1.9854. Min Act: -0.0001
Data Index: 1433805 (Python Code)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2994. Min Range: -2.2994
Max Act: 1.9567. Min Act: -0.0001
Data Index: 1557635 (Python Code)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2994. Min Range: -2.2994
Max Act: 1.9274. Min Act: -0.0001
Data Index: 1439539 (Python Code)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2994. Min Range: -2.2994
Max Act: 1.9010. Min Act: -0.0001
Data Index: 1405430 (Python Code)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2994. Min Range: -2.2994
Max Act: 1.8827. Min Act: -0.0001
Data Index: 1361669 (Python Code)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2994. Min Range: -2.2994
Max Act: 1.7634. Min Act: -0.0001
Data Index: 1602084 (Python Code)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2994. Min Range: -2.2994
Max Act: 1.7533. Min Act: -0.0001
Data Index: 1414661 (Python Code)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2994. Min Range: -2.2994
Max Act: 1.8609. Min Act: -0.0001
Data Index: 1366418 (Python Code)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2994. Min Range: -2.2994
Max Act: 1.9599. Min Act: -0.0001
Data Index: 1498196 (Python Code)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2994. Min Range: -2.2994
Max Act: 1.8475. Min Act: -0.0001
Data Index: 1562108 (Python Code)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2994. Min Range: -2.2994
Max Act: 1.8465. Min Act: -0.0001
Data Index: 1518688 (Python Code)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2994. Min Range: -2.2994
Max Act: 1.7434. Min Act: -0.0001
Data Index: 1398669 (Python Code)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2994. Min Range: -2.2994
Max Act: 1.7291. Min Act: -0.0001
Data Index: 1655993 (Python Code)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2994. Min Range: -2.2994
Max Act: 1.9388. Min Act: -0.0001
Data Index: 1543151 (Python Code)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2994. Min Range: -2.2994
Max Act: 1.8207. Min Act: -0.0001
Data Index: 1492582 (Python Code)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2994. Min Range: -2.2994
Max Act: 1.7135. Min Act: -0.0001
Data Index: 1480548 (Python Code)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #19