Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 927 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 2.3554. Min Range: -2.3554
Max Act: 2.3554. Min Act: -0.0001
Data Index: 1784554 (The Pile)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3554. Min Range: -2.3554
Max Act: 1.9533. Min Act: -0.0001
Data Index: 1504440 (The Pile)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3554. Min Range: -2.3554
Max Act: 2.1073. Min Act: -0.0001
Data Index: 320414 (The Pile)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3554. Min Range: -2.3554
Max Act: 2.0496. Min Act: -0.0001
Data Index: 1009570 (The Pile)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3554. Min Range: -2.3554
Max Act: 1.9483. Min Act: -0.0001
Data Index: 658312 (The Pile)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3554. Min Range: -2.3554
Max Act: 1.9428. Min Act: -0.0001
Data Index: 264650 (The Pile)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3554. Min Range: -2.3554
Max Act: 1.8880. Min Act: -0.0001
Data Index: 1544306 (The Pile)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3554. Min Range: -2.3554
Max Act: 2.0842. Min Act: -0.0001
Data Index: 1811592 (The Pile)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3554. Min Range: -2.3554
Max Act: 1.8902. Min Act: -0.0001
Data Index: 1148163 (The Pile)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3554. Min Range: -2.3554
Max Act: 1.6949. Min Act: -0.0001
Data Index: 1757639 (The Pile)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3554. Min Range: -2.3554
Max Act: 1.8793. Min Act: -0.0001
Data Index: 445534 (The Pile)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3554. Min Range: -2.3554
Max Act: 1.9312. Min Act: -0.0001
Data Index: 1831723 (The Pile)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3554. Min Range: -2.3554
Max Act: 1.7932. Min Act: -0.0001
Data Index: 1345580 (The Pile)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3554. Min Range: -2.3554
Max Act: 1.8457. Min Act: -0.0001
Data Index: 1045087 (The Pile)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3554. Min Range: -2.3554
Max Act: 1.7131. Min Act: -0.0001
Data Index: 1692863 (The Pile)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3554. Min Range: -2.3554
Max Act: 1.7230. Min Act: -0.0001
Data Index: 997567 (The Pile)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3554. Min Range: -2.3554
Max Act: 1.7805. Min Act: -0.0001
Data Index: 189482 (The Pile)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3554. Min Range: -2.3554
Max Act: 1.6978. Min Act: -0.0001
Data Index: 644726 (The Pile)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3554. Min Range: -2.3554
Max Act: 1.6261. Min Act: -0.0001
Data Index: 373986 (The Pile)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3554. Min Range: -2.3554
Max Act: 1.8358. Min Act: -0.0001
Data Index: 584334 (The Pile)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19