Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2811 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.7819. Min Range: -2.7819
Max Act: 2.7819. Min Act: -0.0001
Data Index: 1653462 (Python Code)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7819. Min Range: -2.7819
Max Act: 2.5552. Min Act: -0.0001
Data Index: 1374008 (Python Code)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7819. Min Range: -2.7819
Max Act: 2.4653. Min Act: -0.0001
Data Index: 1470827 (Python Code)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7819. Min Range: -2.7819
Max Act: 2.5933. Min Act: -0.0001
Data Index: 1628258 (Python Code)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7819. Min Range: -2.7819
Max Act: 2.4635. Min Act: -0.0001
Data Index: 1500400 (Python Code)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7819. Min Range: -2.7819
Max Act: 2.4651. Min Act: -0.0001
Data Index: 1476115 (Python Code)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7819. Min Range: -2.7819
Max Act: 2.3371. Min Act: -0.0001
Data Index: 1427650 (Python Code)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7819. Min Range: -2.7819
Max Act: 2.4347. Min Act: -0.0001
Data Index: 1574751 (Python Code)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7819. Min Range: -2.7819
Max Act: 2.3189. Min Act: -0.0001
Data Index: 1451351 (Python Code)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7819. Min Range: -2.7819
Max Act: 2.3473. Min Act: -0.0001
Data Index: 1569954 (Python Code)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7819. Min Range: -2.7819
Max Act: 2.4069. Min Act: -0.0001
Data Index: 1426356 (Python Code)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7819. Min Range: -2.7819
Max Act: 2.3426. Min Act: -0.0001
Data Index: 1473225 (Python Code)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7819. Min Range: -2.7819
Max Act: 2.3864. Min Act: -0.0001
Data Index: 1495591 (Python Code)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7819. Min Range: -2.7819
Max Act: 2.1534. Min Act: -0.0001
Data Index: 1418739 (Python Code)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7819. Min Range: -2.7819
Max Act: 2.1282. Min Act: -0.0001
Data Index: 1494985 (Python Code)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7819. Min Range: -2.7819
Max Act: 2.1819. Min Act: -0.0001
Data Index: 1605185 (Python Code)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7819. Min Range: -2.7819
Max Act: 2.3568. Min Act: -0.0001
Data Index: 1617029 (Python Code)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7819. Min Range: -2.7819
Max Act: 2.2410. Min Act: -0.0001
Data Index: 1379122 (Python Code)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7819. Min Range: -2.7819
Max Act: 2.2743. Min Act: -0.0001
Data Index: 1641041 (Python Code)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7819. Min Range: -2.7819
Max Act: 2.3239. Min Act: -0.0001
Data Index: 1514835 (Python Code)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19