Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 3135 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.4600. Min Range: -0.4600
Max Act: 0.4600. Min Act: -0.0000
Data Index: 84597 (The Pile)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4600. Min Range: -0.4600
Max Act: 0.4475. Min Act: -0.0000
Data Index: 1603144 (The Pile)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4600. Min Range: -0.4600
Max Act: 0.3980. Min Act: -0.0000
Data Index: 589683 (The Pile)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4600. Min Range: -0.4600
Max Act: 0.4182. Min Act: 0.0001
Data Index: 995257 (The Pile)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4600. Min Range: -0.4600
Max Act: 0.3982. Min Act: -0.0000
Data Index: 237303 (The Pile)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4600. Min Range: -0.4600
Max Act: 0.3941. Min Act: -0.0000
Data Index: 119464 (The Pile)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4600. Min Range: -0.4600
Max Act: 0.3823. Min Act: 0.0001
Data Index: 483203 (The Pile)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4600. Min Range: -0.4600
Max Act: 0.3816. Min Act: -0.0000
Data Index: 1859882 (The Pile)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4600. Min Range: -0.4600
Max Act: 0.3483. Min Act: -0.0000
Data Index: 288857 (The Pile)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4600. Min Range: -0.4600
Max Act: 0.3310. Min Act: 0.0000
Data Index: 714849 (The Pile)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4600. Min Range: -0.4600
Max Act: 0.3409. Min Act: -0.0000
Data Index: 1339545 (The Pile)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4600. Min Range: -0.4600
Max Act: 0.3690. Min Act: -0.0000
Data Index: 377239 (The Pile)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4600. Min Range: -0.4600
Max Act: 0.3227. Min Act: -0.0000
Data Index: 721590 (The Pile)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4600. Min Range: -0.4600
Max Act: 0.3197. Min Act: 0.0001
Data Index: 993717 (The Pile)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4600. Min Range: -0.4600
Max Act: 0.3081. Min Act: 0.0000
Data Index: 1660447 (The Pile)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4600. Min Range: -0.4600
Max Act: 0.3003. Min Act: -0.0000
Data Index: 1274720 (The Pile)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4600. Min Range: -0.4600
Max Act: 0.2877. Min Act: -0.0000
Data Index: 832049 (The Pile)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4600. Min Range: -0.4600
Max Act: 0.3131. Min Act: -0.0000
Data Index: 138963 (The Pile)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4600. Min Range: -0.4600
Max Act: 0.2737. Min Act: 0.0000
Data Index: 1343181 (The Pile)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4600. Min Range: -0.4600
Max Act: 0.2868. Min Act: 0.0000
Data Index: 1743227 (The Pile)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19