Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4075 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.4530. Min Range: -2.4530
Max Act: 2.4530. Min Act: -0.0001
Data Index: 1522400 (Python Code)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4530. Min Range: -2.4530
Max Act: 2.2625. Min Act: -0.0001
Data Index: 1481917 (Python Code)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4530. Min Range: -2.4530
Max Act: 2.3003. Min Act: -0.0001
Data Index: 1407080 (Python Code)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4530. Min Range: -2.4530
Max Act: 2.1467. Min Act: -0.0001
Data Index: 1436437 (Python Code)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4530. Min Range: -2.4530
Max Act: 2.3312. Min Act: -0.0001
Data Index: 1477654 (Python Code)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4530. Min Range: -2.4530
Max Act: 2.1488. Min Act: -0.0001
Data Index: 1513510 (Python Code)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4530. Min Range: -2.4530
Max Act: 2.1260. Min Act: -0.0001
Data Index: 1379316 (Python Code)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4530. Min Range: -2.4530
Max Act: 2.1113. Min Act: -0.0001
Data Index: 1399637 (Python Code)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4530. Min Range: -2.4530
Max Act: 2.1533. Min Act: -0.0001
Data Index: 1364562 (Python Code)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4530. Min Range: -2.4530
Max Act: 2.0913. Min Act: -0.0001
Data Index: 1595800 (Python Code)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4530. Min Range: -2.4530
Max Act: 2.1442. Min Act: -0.0001
Data Index: 1426703 (Python Code)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4530. Min Range: -2.4530
Max Act: 2.1460. Min Act: -0.0001
Data Index: 1515979 (Python Code)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4530. Min Range: -2.4530
Max Act: 2.1221. Min Act: -0.0001
Data Index: 1580961 (Python Code)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4530. Min Range: -2.4530
Max Act: 2.0937. Min Act: -0.0001
Data Index: 1491313 (Python Code)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4530. Min Range: -2.4530
Max Act: 2.0742. Min Act: -0.0001
Data Index: 1656772 (Python Code)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4530. Min Range: -2.4530
Max Act: 2.0297. Min Act: -0.0001
Data Index: 1494724 (Python Code)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4530. Min Range: -2.4530
Max Act: 2.1007. Min Act: -0.0001
Data Index: 1519087 (Python Code)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4530. Min Range: -2.4530
Max Act: 2.0527. Min Act: -0.0001
Data Index: 1454757 (Python Code)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4530. Min Range: -2.4530
Max Act: 2.1078. Min Act: -0.0001
Data Index: 1385235 (Python Code)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4530. Min Range: -2.4530
Max Act: 2.0408. Min Act: -0.0001
Data Index: 1403544 (Python Code)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19