Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2225 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.5837. Min Range: -0.5837
Max Act: 0.5837. Min Act: -0.0001
Data Index: 389419 (The Pile)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5837. Min Range: -0.5837
Max Act: 0.5815. Min Act: -0.0001
Data Index: 1160237 (The Pile)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5837. Min Range: -0.5837
Max Act: 0.5499. Min Act: -0.0001
Data Index: 114449 (The Pile)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5837. Min Range: -0.5837
Max Act: 0.4374. Min Act: -0.0001
Data Index: 736983 (The Pile)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5837. Min Range: -0.5837
Max Act: 0.5277. Min Act: -0.0001
Data Index: 712179 (The Pile)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5837. Min Range: -0.5837
Max Act: 0.5063. Min Act: -0.0001
Data Index: 532132 (The Pile)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5837. Min Range: -0.5837
Max Act: 0.5585. Min Act: -0.0001
Data Index: 1378325 (The Pile)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5837. Min Range: -0.5837
Max Act: 0.5477. Min Act: -0.0001
Data Index: 1866313 (The Pile)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5837. Min Range: -0.5837
Max Act: 0.4880. Min Act: -0.0001
Data Index: 89381 (The Pile)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5837. Min Range: -0.5837
Max Act: 0.5183. Min Act: -0.0001
Data Index: 813717 (The Pile)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5837. Min Range: -0.5837
Max Act: 0.4942. Min Act: -0.0001
Data Index: 585184 (The Pile)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5837. Min Range: -0.5837
Max Act: 0.4944. Min Act: -0.0001
Data Index: 985702 (The Pile)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5837. Min Range: -0.5837
Max Act: 0.5033. Min Act: -0.0001
Data Index: 1054663 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5837. Min Range: -0.5837
Max Act: 0.4919. Min Act: -0.0001
Data Index: 1329222 (The Pile)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5837. Min Range: -0.5837
Max Act: 0.3999. Min Act: -0.0001
Data Index: 1326250 (The Pile)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5837. Min Range: -0.5837
Max Act: 0.4398. Min Act: -0.0001
Data Index: 1429337 (The Pile)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5837. Min Range: -0.5837
Max Act: 0.4917. Min Act: -0.0001
Data Index: 1192533 (The Pile)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5837. Min Range: -0.5837
Max Act: 0.4952. Min Act: -0.0001
Data Index: 1014005 (The Pile)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5837. Min Range: -0.5837
Max Act: 0.5112. Min Act: -0.0001
Data Index: 1777707 (The Pile)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5837. Min Range: -0.5837
Max Act: 0.4603. Min Act: -0.0001
Data Index: 790623 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19