Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 520 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.2679. Min Range: -2.2679
Max Act: 2.1980. Min Act: -0.0001
Data Index: 1535824 (Python Code)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2679. Min Range: -2.2679
Max Act: 2.2679. Min Act: -0.0001
Data Index: 1396285 (Python Code)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2679. Min Range: -2.2679
Max Act: 2.2584. Min Act: -0.0001
Data Index: 1652014 (Python Code)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2679. Min Range: -2.2679
Max Act: 2.1696. Min Act: -0.0001
Data Index: 1643354 (Python Code)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2679. Min Range: -2.2679
Max Act: 2.1423. Min Act: -0.0001
Data Index: 7286 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2679. Min Range: -2.2679
Max Act: 2.1093. Min Act: -0.0001
Data Index: 1457087 (Python Code)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2679. Min Range: -2.2679
Max Act: 2.0605. Min Act: -0.0001
Data Index: 1506304 (Python Code)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2679. Min Range: -2.2679
Max Act: 2.0093. Min Act: -0.0001
Data Index: 1430153 (Python Code)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2679. Min Range: -2.2679
Max Act: 2.1378. Min Act: -0.0001
Data Index: 1649392 (Python Code)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2679. Min Range: -2.2679
Max Act: 1.9567. Min Act: -0.0001
Data Index: 1410118 (Python Code)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2679. Min Range: -2.2679
Max Act: 1.9844. Min Act: -0.0001
Data Index: 1409230 (Python Code)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2679. Min Range: -2.2679
Max Act: 1.9946. Min Act: -0.0001
Data Index: 1590227 (Python Code)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2679. Min Range: -2.2679
Max Act: 2.0325. Min Act: -0.0001
Data Index: 1424998 (Python Code)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2679. Min Range: -2.2679
Max Act: 2.1326. Min Act: -0.0001
Data Index: 1447631 (Python Code)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2679. Min Range: -2.2679
Max Act: 1.9536. Min Act: -0.0001
Data Index: 1481483 (Python Code)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2679. Min Range: -2.2679
Max Act: 2.1084. Min Act: -0.0001
Data Index: 1472507 (Python Code)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2679. Min Range: -2.2679
Max Act: 1.9406. Min Act: -0.0001
Data Index: 1402779 (Python Code)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2679. Min Range: -2.2679
Max Act: 1.9835. Min Act: -0.0001
Data Index: 1528401 (Python Code)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2679. Min Range: -2.2679
Max Act: 1.9225. Min Act: -0.0001
Data Index: 1572907 (Python Code)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2679. Min Range: -2.2679
Max Act: 1.9719. Min Act: -0.0001
Data Index: 1540435 (Python Code)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19