Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2497 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.1327. Min Range: -2.1327
Max Act: 2.1281. Min Act: -0.0001
Data Index: 1523124 (Python Code)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1327. Min Range: -2.1327
Max Act: 2.1327. Min Act: -0.0001
Data Index: 1388911 (Python Code)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1327. Min Range: -2.1327
Max Act: 2.0325. Min Act: -0.0001
Data Index: 1480799 (Python Code)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1327. Min Range: -2.1327
Max Act: 1.9795. Min Act: -0.0001
Data Index: 1413501 (Python Code)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1327. Min Range: -2.1327
Max Act: 2.0288. Min Act: -0.0001
Data Index: 1524968 (Python Code)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1327. Min Range: -2.1327
Max Act: 1.9838. Min Act: -0.0001
Data Index: 1533021 (Python Code)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1327. Min Range: -2.1327
Max Act: 1.9728. Min Act: -0.0001
Data Index: 1399772 (Python Code)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1327. Min Range: -2.1327
Max Act: 2.0044. Min Act: -0.0001
Data Index: 1371742 (Python Code)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1327. Min Range: -2.1327
Max Act: 1.9658. Min Act: -0.0001
Data Index: 1578873 (Python Code)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1327. Min Range: -2.1327
Max Act: 2.0324. Min Act: -0.0001
Data Index: 1503155 (Python Code)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1327. Min Range: -2.1327
Max Act: 1.9711. Min Act: -0.0001
Data Index: 1575982 (Python Code)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1327. Min Range: -2.1327
Max Act: 1.9480. Min Act: -0.0001
Data Index: 1541973 (Python Code)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1327. Min Range: -2.1327
Max Act: 1.9978. Min Act: -0.0001
Data Index: 1552496 (Python Code)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1327. Min Range: -2.1327
Max Act: 1.9955. Min Act: -0.0001
Data Index: 1424127 (Python Code)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1327. Min Range: -2.1327
Max Act: 1.8403. Min Act: -0.0001
Data Index: 1555333 (Python Code)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1327. Min Range: -2.1327
Max Act: 1.8814. Min Act: -0.0001
Data Index: 1613300 (Python Code)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1327. Min Range: -2.1327
Max Act: 1.8430. Min Act: -0.0001
Data Index: 1485062 (Python Code)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1327. Min Range: -2.1327
Max Act: 1.9482. Min Act: -0.0001
Data Index: 1436481 (Python Code)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1327. Min Range: -2.1327
Max Act: 1.8786. Min Act: -0.0001
Data Index: 1423572 (Python Code)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1327. Min Range: -2.1327
Max Act: 1.8484. Min Act: -0.0001
Data Index: 1539208 (Python Code)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #19