Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2698 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.0576. Min Range: -2.0576
Max Act: 2.0576. Min Act: -0.0000
Data Index: 422825 (The Pile)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0576. Min Range: -2.0576
Max Act: 1.9177. Min Act: -0.0000
Data Index: 917178 (The Pile)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0576. Min Range: -2.0576
Max Act: 1.7476. Min Act: -0.0000
Data Index: 858072 (The Pile)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0576. Min Range: -2.0576
Max Act: 1.6265. Min Act: -0.0000
Data Index: 556916 (The Pile)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0576. Min Range: -2.0576
Max Act: 1.8093. Min Act: -0.0000
Data Index: 422782 (The Pile)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0576. Min Range: -2.0576
Max Act: 1.7996. Min Act: -0.0000
Data Index: 1101254 (The Pile)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0576. Min Range: -2.0576
Max Act: 1.7137. Min Act: -0.0000
Data Index: 645464 (The Pile)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0576. Min Range: -2.0576
Max Act: 1.6268. Min Act: -0.0000
Data Index: 946503 (The Pile)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0576. Min Range: -2.0576
Max Act: 1.7436. Min Act: -0.0000
Data Index: 1392778 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0576. Min Range: -2.0576
Max Act: 1.6838. Min Act: -0.0000
Data Index: 1399804 (The Pile)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0576. Min Range: -2.0576
Max Act: 1.5983. Min Act: -0.0000
Data Index: 218986 (The Pile)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0576. Min Range: -2.0576
Max Act: 1.7293. Min Act: -0.0000
Data Index: 940549 (The Pile)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0576. Min Range: -2.0576
Max Act: 1.6305. Min Act: -0.0000
Data Index: 353987 (The Pile)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0576. Min Range: -2.0576
Max Act: 1.7101. Min Act: -0.0000
Data Index: 1081960 (The Pile)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0576. Min Range: -2.0576
Max Act: 1.5727. Min Act: -0.0000
Data Index: 528220 (The Pile)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0576. Min Range: -2.0576
Max Act: 1.5553. Min Act: -0.0000
Data Index: 457476 (The Pile)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0576. Min Range: -2.0576
Max Act: 1.5951. Min Act: -0.0000
Data Index: 1971663 (The Pile)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0576. Min Range: -2.0576
Max Act: 1.6329. Min Act: -0.0000
Data Index: 897171 (The Pile)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0576. Min Range: -2.0576
Max Act: 1.6496. Min Act: -0.0000
Data Index: 1237720 (The Pile)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0576. Min Range: -2.0576
Max Act: 1.5577. Min Act: -0.0000
Data Index: 706698 (The Pile)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #19