Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1171 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.1496. Min Range: -0.1496
Max Act: 0.1496. Min Act: -0.0001
Data Index: 963806 (The Pile)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1496. Min Range: -0.1496
Max Act: 0.1322. Min Act: -0.0001
Data Index: 242623 (The Pile)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1496. Min Range: -0.1496
Max Act: 0.1377. Min Act: -0.0001
Data Index: 1670077 (The Pile)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1496. Min Range: -0.1496
Max Act: 0.1305. Min Act: -0.0001
Data Index: 543242 (The Pile)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1496. Min Range: -0.1496
Max Act: 0.1216. Min Act: -0.0001
Data Index: 501772 (The Pile)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1496. Min Range: -0.1496
Max Act: 0.1287. Min Act: -0.0001
Data Index: 717581 (The Pile)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1496. Min Range: -0.1496
Max Act: 0.1385. Min Act: -0.0001
Data Index: 969692 (The Pile)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1496. Min Range: -0.1496
Max Act: 0.1281. Min Act: -0.0001
Data Index: 1503049 (The Pile)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1496. Min Range: -0.1496
Max Act: 0.1320. Min Act: -0.0001
Data Index: 1545124 (The Pile)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1496. Min Range: -0.1496
Max Act: 0.1283. Min Act: -0.0001
Data Index: 825920 (The Pile)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1496. Min Range: -0.1496
Max Act: 0.1264. Min Act: -0.0001
Data Index: 823527 (The Pile)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1496. Min Range: -0.1496
Max Act: 0.1302. Min Act: -0.0001
Data Index: 1729103 (The Pile)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1496. Min Range: -0.1496
Max Act: 0.1256. Min Act: -0.0001
Data Index: 1812526 (The Pile)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1496. Min Range: -0.1496
Max Act: 0.1346. Min Act: -0.0001
Data Index: 1970523 (The Pile)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1496. Min Range: -0.1496
Max Act: 0.1315. Min Act: -0.0001
Data Index: 1543544 (The Pile)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1496. Min Range: -0.1496
Max Act: 0.1441. Min Act: -0.0001
Data Index: 1790555 (The Pile)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1496. Min Range: -0.1496
Max Act: 0.1244. Min Act: -0.0001
Data Index: 511047 (The Pile)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1496. Min Range: -0.1496
Max Act: 0.1302. Min Act: -0.0001
Data Index: 590640 (The Pile)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1496. Min Range: -0.1496
Max Act: 0.1281. Min Act: -0.0001
Data Index: 100740 (The Pile)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1496. Min Range: -0.1496
Max Act: 0.1345. Min Act: -0.0001
Data Index: 853904 (The Pile)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19