Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 208 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.1117. Min Range: -1.1117
Max Act: 1.1117. Min Act: -0.0001
Data Index: 1381334 (The Pile)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1117. Min Range: -1.1117
Max Act: 1.0556. Min Act: -0.0001
Data Index: 1133631 (The Pile)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1117. Min Range: -1.1117
Max Act: 0.9816. Min Act: -0.0001
Data Index: 900878 (The Pile)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1117. Min Range: -1.1117
Max Act: 1.0589. Min Act: -0.0001
Data Index: 818838 (The Pile)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1117. Min Range: -1.1117
Max Act: 0.8904. Min Act: -0.0001
Data Index: 1031524 (The Pile)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1117. Min Range: -1.1117
Max Act: 1.0923. Min Act: -0.0001
Data Index: 1545333 (The Pile)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1117. Min Range: -1.1117
Max Act: 0.9240. Min Act: -0.0001
Data Index: 1656183 (The Pile)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1117. Min Range: -1.1117
Max Act: 0.9488. Min Act: -0.0001
Data Index: 690331 (The Pile)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1117. Min Range: -1.1117
Max Act: 0.8710. Min Act: -0.0001
Data Index: 932307 (The Pile)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1117. Min Range: -1.1117
Max Act: 1.0139. Min Act: -0.0001
Data Index: 83078 (The Pile)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1117. Min Range: -1.1117
Max Act: 0.7605. Min Act: -0.0001
Data Index: 139165 (The Pile)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1117. Min Range: -1.1117
Max Act: 0.8468. Min Act: -0.0001
Data Index: 1660712 (The Pile)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1117. Min Range: -1.1117
Max Act: 0.8437. Min Act: -0.0001
Data Index: 1060982 (The Pile)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1117. Min Range: -1.1117
Max Act: 0.7136. Min Act: -0.0001
Data Index: 1721620 (The Pile)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1117. Min Range: -1.1117
Max Act: 0.7757. Min Act: -0.0001
Data Index: 244134 (The Pile)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1117. Min Range: -1.1117
Max Act: 0.8199. Min Act: -0.0001
Data Index: 242151 (The Pile)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1117. Min Range: -1.1117
Max Act: 0.7778. Min Act: -0.0001
Data Index: 924341 (The Pile)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1117. Min Range: -1.1117
Max Act: 0.7787. Min Act: -0.0001
Data Index: 1664427 (The Pile)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1117. Min Range: -1.1117
Max Act: 0.7441. Min Act: -0.0001
Data Index: 616819 (The Pile)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1117. Min Range: -1.1117
Max Act: 0.6964. Min Act: -0.0001
Data Index: 875268 (The Pile)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19