Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 531 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.0150. Min Range: -1.0150
Max Act: 1.0150. Min Act: -0.0001
Data Index: 1161765 (The Pile)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0150. Min Range: -1.0150
Max Act: 0.9126. Min Act: -0.0001
Data Index: 867867 (The Pile)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0150. Min Range: -1.0150
Max Act: 0.9070. Min Act: -0.0001
Data Index: 1323412 (The Pile)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0150. Min Range: -1.0150
Max Act: 0.9213. Min Act: -0.0001
Data Index: 536673 (The Pile)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0150. Min Range: -1.0150
Max Act: 0.8785. Min Act: -0.0001
Data Index: 1740764 (The Pile)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0150. Min Range: -1.0150
Max Act: 0.8732. Min Act: -0.0001
Data Index: 1681844 (The Pile)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0150. Min Range: -1.0150
Max Act: 0.9423. Min Act: -0.0001
Data Index: 988824 (The Pile)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0150. Min Range: -1.0150
Max Act: 0.8622. Min Act: -0.0001
Data Index: 339647 (The Pile)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0150. Min Range: -1.0150
Max Act: 0.9055. Min Act: -0.0001
Data Index: 115466 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0150. Min Range: -1.0150
Max Act: 0.8453. Min Act: -0.0001
Data Index: 1088186 (The Pile)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0150. Min Range: -1.0150
Max Act: 0.7985. Min Act: -0.0001
Data Index: 416508 (The Pile)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0150. Min Range: -1.0150
Max Act: 0.8651. Min Act: -0.0001
Data Index: 646445 (The Pile)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0150. Min Range: -1.0150
Max Act: 0.8094. Min Act: -0.0001
Data Index: 1575191 (The Pile)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0150. Min Range: -1.0150
Max Act: 0.7818. Min Act: -0.0001
Data Index: 68609 (The Pile)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0150. Min Range: -1.0150
Max Act: 0.8755. Min Act: -0.0001
Data Index: 1064943 (The Pile)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0150. Min Range: -1.0150
Max Act: 0.8326. Min Act: -0.0001
Data Index: 266695 (The Pile)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0150. Min Range: -1.0150
Max Act: 0.8637. Min Act: -0.0001
Data Index: 1210255 (The Pile)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0150. Min Range: -1.0150
Max Act: 0.8216. Min Act: -0.0001
Data Index: 1437637 (The Pile)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0150. Min Range: -1.0150
Max Act: 0.8813. Min Act: -0.0001
Data Index: 1447113 (The Pile)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0150. Min Range: -1.0150
Max Act: 0.8175. Min Act: -0.0001
Data Index: 907023 (The Pile)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #19