Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 2144 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 0.9967. Min Range: -0.9967
Max Act: 0.9967. Min Act: -0.0003
Data Index: 773222 (The Pile)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9967. Min Range: -0.9967
Max Act: 0.7087. Min Act: -0.0003
Data Index: 1363633 (The Pile)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9967. Min Range: -0.9967
Max Act: 0.7295. Min Act: -0.0003
Data Index: 1577034 (The Pile)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9967. Min Range: -0.9967
Max Act: 0.6916. Min Act: -0.0003
Data Index: 242920 (The Pile)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9967. Min Range: -0.9967
Max Act: 0.6868. Min Act: -0.0003
Data Index: 849300 (The Pile)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9967. Min Range: -0.9967
Max Act: 0.6937. Min Act: -0.0003
Data Index: 1427188 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9967. Min Range: -0.9967
Max Act: 0.6944. Min Act: -0.0003
Data Index: 746900 (The Pile)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9967. Min Range: -0.9967
Max Act: 0.6617. Min Act: -0.0003
Data Index: 30370 (The Pile)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9967. Min Range: -0.9967
Max Act: 0.6940. Min Act: -0.0003
Data Index: 330108 (The Pile)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9967. Min Range: -0.9967
Max Act: 0.6743. Min Act: -0.0003
Data Index: 981696 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9967. Min Range: -0.9967
Max Act: 0.6470. Min Act: -0.0003
Data Index: 1326078 (The Pile)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9967. Min Range: -0.9967
Max Act: 0.6278. Min Act: -0.0003
Data Index: 1133672 (The Pile)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9967. Min Range: -0.9967
Max Act: 0.6576. Min Act: -0.0003
Data Index: 66162 (The Pile)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9967. Min Range: -0.9967
Max Act: 0.6589. Min Act: -0.0003
Data Index: 783755 (The Pile)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9967. Min Range: -0.9967
Max Act: 0.6557. Min Act: -0.0003
Data Index: 1856186 (The Pile)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9967. Min Range: -0.9967
Max Act: 0.6467. Min Act: -0.0003
Data Index: 616342 (The Pile)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9967. Min Range: -0.9967
Max Act: 0.6666. Min Act: -0.0003
Data Index: 1953694 (The Pile)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9967. Min Range: -0.9967
Max Act: 0.6417. Min Act: -0.0003
Data Index: 1930746 (The Pile)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9967. Min Range: -0.9967
Max Act: 0.6242. Min Act: -0.0003
Data Index: 1112944 (The Pile)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9967. Min Range: -0.9967
Max Act: 0.6376. Min Act: -0.0003
Data Index: 1311470 (The Pile)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #19