Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1638 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.8786. Min Range: -0.8786
Max Act: 0.8786. Min Act: -0.0001
Data Index: 100213 (The Pile)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8786. Min Range: -0.8786
Max Act: 0.7832. Min Act: -0.0001
Data Index: 1247922 (The Pile)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8786. Min Range: -0.8786
Max Act: 0.8108. Min Act: -0.0001
Data Index: 355764 (The Pile)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8786. Min Range: -0.8786
Max Act: 0.7101. Min Act: -0.0001
Data Index: 1300565 (The Pile)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8786. Min Range: -0.8786
Max Act: 0.7000. Min Act: -0.0001
Data Index: 1153385 (The Pile)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8786. Min Range: -0.8786
Max Act: 0.6230. Min Act: -0.0001
Data Index: 1173389 (The Pile)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8786. Min Range: -0.8786
Max Act: 0.7296. Min Act: -0.0001
Data Index: 1212593 (The Pile)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8786. Min Range: -0.8786
Max Act: 0.7531. Min Act: -0.0001
Data Index: 1295783 (The Pile)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8786. Min Range: -0.8786
Max Act: 0.6223. Min Act: -0.0001
Data Index: 951547 (The Pile)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8786. Min Range: -0.8786
Max Act: 0.6489. Min Act: -0.0001
Data Index: 1152602 (The Pile)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8786. Min Range: -0.8786
Max Act: 0.6972. Min Act: -0.0001
Data Index: 382325 (The Pile)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8786. Min Range: -0.8786
Max Act: 0.6557. Min Act: -0.0001
Data Index: 1734603 (The Pile)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8786. Min Range: -0.8786
Max Act: 0.6410. Min Act: -0.0001
Data Index: 1421319 (The Pile)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8786. Min Range: -0.8786
Max Act: 0.7267. Min Act: -0.0001
Data Index: 1432306 (The Pile)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8786. Min Range: -0.8786
Max Act: 0.6562. Min Act: -0.0001
Data Index: 690791 (The Pile)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8786. Min Range: -0.8786
Max Act: 0.6199. Min Act: -0.0001
Data Index: 30830 (The Pile)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8786. Min Range: -0.8786
Max Act: 0.6392. Min Act: -0.0001
Data Index: 1807265 (The Pile)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8786. Min Range: -0.8786
Max Act: 0.6229. Min Act: -0.0001
Data Index: 1991801 (The Pile)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8786. Min Range: -0.8786
Max Act: 0.6000. Min Act: -0.0001
Data Index: 37231 (The Pile)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8786. Min Range: -0.8786
Max Act: 0.6505. Min Act: -0.0001
Data Index: 69634 (The Pile)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19