Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1947 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 3.2491. Min Range: -3.2491
Max Act: 3.2491. Min Act: -0.0001
Data Index: 1538832 (Python Code)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2491. Min Range: -3.2491
Max Act: 2.4110. Min Act: -0.0001
Data Index: 1624153 (Python Code)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2491. Min Range: -3.2491
Max Act: 2.5033. Min Act: -0.0001
Data Index: 1582466 (Python Code)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2491. Min Range: -3.2491
Max Act: 2.4400. Min Act: -0.0001
Data Index: 1559319 (Python Code)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2491. Min Range: -3.2491
Max Act: 2.3542. Min Act: -0.0001
Data Index: 1472922 (Python Code)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2491. Min Range: -3.2491
Max Act: 2.1079. Min Act: -0.0001
Data Index: 1430737 (Python Code)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2491. Min Range: -3.2491
Max Act: 2.1613. Min Act: -0.0001
Data Index: 1614657 (Python Code)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2491. Min Range: -3.2491
Max Act: 2.1955. Min Act: -0.0001
Data Index: 1375935 (Python Code)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2491. Min Range: -3.2491
Max Act: 2.0326. Min Act: -0.0001
Data Index: 1539141 (Python Code)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2491. Min Range: -3.2491
Max Act: 2.0766. Min Act: -0.0001
Data Index: 1536297 (Python Code)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2491. Min Range: -3.2491
Max Act: 2.0870. Min Act: -0.0001
Data Index: 1467516 (Python Code)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2491. Min Range: -3.2491
Max Act: 2.0981. Min Act: -0.0001
Data Index: 1477976 (Python Code)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2491. Min Range: -3.2491
Max Act: 2.2096. Min Act: -0.0001
Data Index: 1370116 (Python Code)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2491. Min Range: -3.2491
Max Act: 2.0313. Min Act: -0.0001
Data Index: 1502557 (Python Code)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2491. Min Range: -3.2491
Max Act: 2.1362. Min Act: -0.0001
Data Index: 1367667 (Python Code)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2491. Min Range: -3.2491
Max Act: 2.0854. Min Act: -0.0001
Data Index: 1631821 (Python Code)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2491. Min Range: -3.2491
Max Act: 2.0787. Min Act: -0.0001
Data Index: 1529092 (Python Code)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2491. Min Range: -3.2491
Max Act: 2.1222. Min Act: -0.0001
Data Index: 1586811 (Python Code)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2491. Min Range: -3.2491
Max Act: 2.0108. Min Act: -0.0001
Data Index: 1435843 (Python Code)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2491. Min Range: -3.2491
Max Act: 2.0616. Min Act: -0.0001
Data Index: 1473792 (Python Code)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19