Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2819 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.6502. Min Range: -1.6502
Max Act: 1.6502. Min Act: -0.0001
Data Index: 1384739 (Python Code)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6502. Min Range: -1.6502
Max Act: 1.5062. Min Act: -0.0001
Data Index: 1557265 (Python Code)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6502. Min Range: -1.6502
Max Act: 1.2994. Min Act: -0.0001
Data Index: 1449652 (Python Code)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6502. Min Range: -1.6502
Max Act: 1.3481. Min Act: -0.0001
Data Index: 1579568 (Python Code)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6502. Min Range: -1.6502
Max Act: 1.2958. Min Act: -0.0001
Data Index: 1648429 (Python Code)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6502. Min Range: -1.6502
Max Act: 1.1872. Min Act: -0.0001
Data Index: 1498094 (Python Code)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6502. Min Range: -1.6502
Max Act: 1.1248. Min Act: -0.0001
Data Index: 1450524 (Python Code)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6502. Min Range: -1.6502
Max Act: 1.2096. Min Act: -0.0001
Data Index: 1501176 (Python Code)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6502. Min Range: -1.6502
Max Act: 1.1032. Min Act: -0.0001
Data Index: 1527126 (Python Code)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6502. Min Range: -1.6502
Max Act: 1.0886. Min Act: -0.0001
Data Index: 1528223 (Python Code)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6502. Min Range: -1.6502
Max Act: 1.1128. Min Act: -0.0001
Data Index: 1361662 (Python Code)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6502. Min Range: -1.6502
Max Act: 1.0913. Min Act: -0.0001
Data Index: 1514990 (Python Code)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6502. Min Range: -1.6502
Max Act: 1.0403. Min Act: -0.0001
Data Index: 1553634 (Python Code)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6502. Min Range: -1.6502
Max Act: 1.0093. Min Act: -0.0001
Data Index: 1643425 (Python Code)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6502. Min Range: -1.6502
Max Act: 0.9999. Min Act: -0.0001
Data Index: 1493224 (Python Code)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6502. Min Range: -1.6502
Max Act: 1.0220. Min Act: -0.0001
Data Index: 1449363 (Python Code)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6502. Min Range: -1.6502
Max Act: 0.9203. Min Act: -0.0001
Data Index: 1457929 (Python Code)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6502. Min Range: -1.6502
Max Act: 1.0422. Min Act: -0.0001
Data Index: 1567950 (Python Code)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6502. Min Range: -1.6502
Max Act: 0.9426. Min Act: -0.0001
Data Index: 1429857 (Python Code)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6502. Min Range: -1.6502
Max Act: 1.0335. Min Act: -0.0001
Data Index: 1595208 (Python Code)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19