Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3675 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 4.5454. Min Range: -4.5454
Max Act: 4.5454. Min Act: -0.0001
Data Index: 1480962 (Python Code)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5454. Min Range: -4.5454
Max Act: 3.8936. Min Act: -0.0001
Data Index: 1386412 (Python Code)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5454. Min Range: -4.5454
Max Act: 3.2556. Min Act: -0.0001
Data Index: 1425557 (Python Code)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5454. Min Range: -4.5454
Max Act: 2.5088. Min Act: -0.0001
Data Index: 1579577 (Python Code)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5454. Min Range: -4.5454
Max Act: 2.8843. Min Act: -0.0001
Data Index: 1413006 (Python Code)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5454. Min Range: -4.5454
Max Act: 2.8192. Min Act: -0.0001
Data Index: 561946 (C4 (Web Text))
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5454. Min Range: -4.5454
Max Act: 2.6538. Min Act: -0.0001
Data Index: 652001 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5454. Min Range: -4.5454
Max Act: 2.6162. Min Act: -0.0001
Data Index: 1382025 (Python Code)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5454. Min Range: -4.5454
Max Act: 2.5350. Min Act: -0.0001
Data Index: 1374673 (Python Code)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5454. Min Range: -4.5454
Max Act: 2.5312. Min Act: -0.0001
Data Index: 1600643 (Python Code)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5454. Min Range: -4.5454
Max Act: 2.5136. Min Act: -0.0001
Data Index: 1457238 (Python Code)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5454. Min Range: -4.5454
Max Act: 2.5100. Min Act: -0.0001
Data Index: 1379247 (Python Code)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5454. Min Range: -4.5454
Max Act: 2.3794. Min Act: -0.0001
Data Index: 1441360 (Python Code)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5454. Min Range: -4.5454
Max Act: 2.4593. Min Act: -0.0001
Data Index: 1603119 (Python Code)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5454. Min Range: -4.5454
Max Act: 2.2764. Min Act: -0.0001
Data Index: 1474981 (Python Code)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5454. Min Range: -4.5454
Max Act: 2.3847. Min Act: -0.0001
Data Index: 1440386 (Python Code)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5454. Min Range: -4.5454
Max Act: 2.2606. Min Act: -0.0001
Data Index: 1627105 (Python Code)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5454. Min Range: -4.5454
Max Act: 2.2452. Min Act: -0.0001
Data Index: 1446525 (Python Code)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5454. Min Range: -4.5454
Max Act: 2.3847. Min Act: -0.0001
Data Index: 1459740 (Python Code)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5454. Min Range: -4.5454
Max Act: 2.2559. Min Act: -0.0001
Data Index: 1499878 (Python Code)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19