Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 3531 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.0934. Min Range: -1.0934
Max Act: 1.0934. Min Act: -0.0000
Data Index: 1085907 (The Pile)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0934. Min Range: -1.0934
Max Act: 1.0493. Min Act: -0.0000
Data Index: 952804 (The Pile)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0934. Min Range: -1.0934
Max Act: 0.9942. Min Act: -0.0000
Data Index: 825454 (The Pile)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0934. Min Range: -1.0934
Max Act: 1.0388. Min Act: -0.0000
Data Index: 1526765 (The Pile)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0934. Min Range: -1.0934
Max Act: 0.9399. Min Act: -0.0000
Data Index: 963397 (The Pile)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0934. Min Range: -1.0934
Max Act: 0.9744. Min Act: -0.0000
Data Index: 1456555 (The Pile)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0934. Min Range: -1.0934
Max Act: 0.9530. Min Act: -0.0000
Data Index: 1557887 (The Pile)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0934. Min Range: -1.0934
Max Act: 0.9535. Min Act: -0.0000
Data Index: 1195111 (The Pile)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0934. Min Range: -1.0934
Max Act: 0.9234. Min Act: -0.0000
Data Index: 723288 (The Pile)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0934. Min Range: -1.0934
Max Act: 0.9824. Min Act: 0.0001
Data Index: 991116 (The Pile)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0934. Min Range: -1.0934
Max Act: 0.9642. Min Act: -0.0000
Data Index: 136040 (The Pile)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0934. Min Range: -1.0934
Max Act: 0.8848. Min Act: -0.0000
Data Index: 1522946 (The Pile)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0934. Min Range: -1.0934
Max Act: 0.9162. Min Act: -0.0000
Data Index: 178273 (The Pile)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0934. Min Range: -1.0934
Max Act: 0.8442. Min Act: -0.0000
Data Index: 140030 (The Pile)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0934. Min Range: -1.0934
Max Act: 0.8372. Min Act: -0.0000
Data Index: 743901 (The Pile)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0934. Min Range: -1.0934
Max Act: 0.9182. Min Act: -0.0000
Data Index: 111912 (The Pile)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0934. Min Range: -1.0934
Max Act: 0.8396. Min Act: -0.0000
Data Index: 801450 (The Pile)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0934. Min Range: -1.0934
Max Act: 0.8497. Min Act: -0.0000
Data Index: 1093277 (The Pile)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0934. Min Range: -1.0934
Max Act: 0.8304. Min Act: 0.0000
Data Index: 401252 (The Pile)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0934. Min Range: -1.0934
Max Act: 0.8417. Min Act: -0.0000
Data Index: 230404 (The Pile)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19