Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4413 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.1810. Min Range: -0.1810
Max Act: 0.1790. Min Act: -0.0001
Data Index: 442305 (C4 (Web Text))
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1810. Min Range: -0.1810
Max Act: 0.1810. Min Act: -0.0002
Data Index: 1311100 (C4 (Web Text))
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1810. Min Range: -0.1810
Max Act: 0.1633. Min Act: -0.0001
Data Index: 367674 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1810. Min Range: -0.1810
Max Act: 0.1611. Min Act: -0.0001
Data Index: 1173882 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1810. Min Range: -0.1810
Max Act: 0.1717. Min Act: -0.0001
Data Index: 728262 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1810. Min Range: -0.1810
Max Act: 0.1493. Min Act: -0.0001
Data Index: 167239 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1810. Min Range: -0.1810
Max Act: 0.1537. Min Act: -0.0001
Data Index: 231577 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1810. Min Range: -0.1810
Max Act: 0.1499. Min Act: -0.0001
Data Index: 1132380 (C4 (Web Text))
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1810. Min Range: -0.1810
Max Act: 0.1565. Min Act: -0.0001
Data Index: 824907 (C4 (Web Text))
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1810. Min Range: -0.1810
Max Act: 0.1432. Min Act: -0.0001
Data Index: 1269487 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1810. Min Range: -0.1810
Max Act: 0.1442. Min Act: -0.0001
Data Index: 1323211 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1810. Min Range: -0.1810
Max Act: 0.1410. Min Act: -0.0001
Data Index: 438651 (C4 (Web Text))
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1810. Min Range: -0.1810
Max Act: 0.1367. Min Act: -0.0001
Data Index: 1095218 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1810. Min Range: -0.1810
Max Act: 0.1372. Min Act: -0.0001
Data Index: 1310489 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1810. Min Range: -0.1810
Max Act: 0.1199. Min Act: -0.0001
Data Index: 867295 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1810. Min Range: -0.1810
Max Act: 0.1327. Min Act: -0.0001
Data Index: 993710 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1810. Min Range: -0.1810
Max Act: 0.1225. Min Act: -0.0001
Data Index: 1309009 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1810. Min Range: -0.1810
Max Act: 0.1335. Min Act: -0.0001
Data Index: 1204689 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1810. Min Range: -0.1810
Max Act: 0.1379. Min Act: -0.0001
Data Index: 83680 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1810. Min Range: -0.1810
Max Act: 0.1213. Min Act: -0.0001
Data Index: 157519 (C4 (Web Text))
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19