Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3150 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.6525. Min Range: -3.6525
Max Act: 3.4259. Min Act: -0.0001
Data Index: 1405660 (Python Code)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6525. Min Range: -3.6525
Max Act: 3.6525. Min Act: -0.0001
Data Index: 866632 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6525. Min Range: -3.6525
Max Act: 3.0961. Min Act: -0.0001
Data Index: 1364075 (Python Code)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6525. Min Range: -3.6525
Max Act: 2.9637. Min Act: -0.0001
Data Index: 1490853 (Python Code)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6525. Min Range: -3.6525
Max Act: 2.8508. Min Act: -0.0001
Data Index: 832595 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6525. Min Range: -3.6525
Max Act: 2.9768. Min Act: -0.0001
Data Index: 788485 (C4 (Web Text))
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6525. Min Range: -3.6525
Max Act: 2.8119. Min Act: -0.0001
Data Index: 325732 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6525. Min Range: -3.6525
Max Act: 2.8077. Min Act: -0.0001
Data Index: 1653055 (Python Code)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6525. Min Range: -3.6525
Max Act: 2.9072. Min Act: -0.0001
Data Index: 155253 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6525. Min Range: -3.6525
Max Act: 2.7268. Min Act: -0.0001
Data Index: 1638893 (Python Code)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6525. Min Range: -3.6525
Max Act: 2.5489. Min Act: -0.0001
Data Index: 520593 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6525. Min Range: -3.6525
Max Act: 2.6969. Min Act: -0.0001
Data Index: 1629569 (Python Code)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6525. Min Range: -3.6525
Max Act: 2.8246. Min Act: -0.0001
Data Index: 496947 (C4 (Web Text))
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6525. Min Range: -3.6525
Max Act: 2.6852. Min Act: -0.0001
Data Index: 1475613 (Python Code)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6525. Min Range: -3.6525
Max Act: 2.3976. Min Act: -0.0001
Data Index: 1285389 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6525. Min Range: -3.6525
Max Act: 2.8137. Min Act: -0.0001
Data Index: 408921 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6525. Min Range: -3.6525
Max Act: 2.6348. Min Act: -0.0001
Data Index: 1522338 (Python Code)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6525. Min Range: -3.6525
Max Act: 2.7393. Min Act: -0.0001
Data Index: 1656302 (Python Code)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6525. Min Range: -3.6525
Max Act: 2.8855. Min Act: -0.0001
Data Index: 1530052 (Python Code)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6525. Min Range: -3.6525
Max Act: 2.7480. Min Act: -0.0001
Data Index: 1374896 (Python Code)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #19