Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2911 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 3.0008. Min Range: -3.0008
Max Act: 3.0008. Min Act: -0.0001
Data Index: 1487997 (Python Code)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0008. Min Range: -3.0008
Max Act: 2.2338. Min Act: -0.0001
Data Index: 113343 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0008. Min Range: -3.0008
Max Act: 2.3716. Min Act: -0.0001
Data Index: 1584493 (Python Code)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0008. Min Range: -3.0008
Max Act: 2.2246. Min Act: -0.0001
Data Index: 434603 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0008. Min Range: -3.0008
Max Act: 2.1514. Min Act: -0.0001
Data Index: 1393193 (Python Code)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0008. Min Range: -3.0008
Max Act: 2.1882. Min Act: -0.0001
Data Index: 1598042 (Python Code)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0008. Min Range: -3.0008
Max Act: 2.2119. Min Act: -0.0001
Data Index: 319535 (C4 (Web Text))
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0008. Min Range: -3.0008
Max Act: 2.2224. Min Act: -0.0001
Data Index: 1634087 (Python Code)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0008. Min Range: -3.0008
Max Act: 2.1940. Min Act: -0.0001
Data Index: 1456787 (Python Code)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0008. Min Range: -3.0008
Max Act: 2.1256. Min Act: -0.0001
Data Index: 39357 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0008. Min Range: -3.0008
Max Act: 1.8650. Min Act: -0.0001
Data Index: 1109358 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0008. Min Range: -3.0008
Max Act: 2.2477. Min Act: -0.0001
Data Index: 1287766 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0008. Min Range: -3.0008
Max Act: 1.8965. Min Act: -0.0001
Data Index: 350110 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0008. Min Range: -3.0008
Max Act: 1.8953. Min Act: -0.0001
Data Index: 110347 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0008. Min Range: -3.0008
Max Act: 2.0236. Min Act: -0.0001
Data Index: 596613 (C4 (Web Text))
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0008. Min Range: -3.0008
Max Act: 1.9436. Min Act: -0.0001
Data Index: 798518 (C4 (Web Text))
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0008. Min Range: -3.0008
Max Act: 1.9985. Min Act: -0.0001
Data Index: 762274 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0008. Min Range: -3.0008
Max Act: 2.1484. Min Act: -0.0001
Data Index: 1083450 (C4 (Web Text))
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0008. Min Range: -3.0008
Max Act: 1.9839. Min Act: -0.0001
Data Index: 575491 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0008. Min Range: -3.0008
Max Act: 1.9152. Min Act: -0.0001
Data Index: 92208 (C4 (Web Text))
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19