Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 640 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.3407. Min Act: -0.0000

Data Index: 1184601 (The Pile)

Max Activating Token Index: 223

Text #1

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2930. Min Act: -0.0000

Data Index: 1549759 (The Pile)

Max Activating Token Index: 60

Text #2

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2983. Min Act: -0.0000

Data Index: 252175 (The Pile)

Max Activating Token Index: 297

Text #3

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.3101. Min Act: -0.0000

Data Index: 1782109 (The Pile)

Max Activating Token Index: 241

Text #4

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.3062. Min Act: -0.0000

Data Index: 1429096 (The Pile)

Max Activating Token Index: 325

Text #5

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2933. Min Act: -0.0000

Data Index: 1331155 (The Pile)

Max Activating Token Index: 247

Text #6

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2739. Min Act: -0.0000

Data Index: 865635 (The Pile)

Max Activating Token Index: 968

Text #7

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2775. Min Act: -0.0000

Data Index: 1697900 (The Pile)

Max Activating Token Index: 829

Text #8

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2850. Min Act: -0.0000

Data Index: 12849 (The Pile)

Max Activating Token Index: 715

Text #9

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2801. Min Act: -0.0000

Data Index: 1494525 (The Pile)

Max Activating Token Index: 256

Text #10

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2841. Min Act: -0.0000

Data Index: 1996365 (The Pile)

Max Activating Token Index: 469

Text #11

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2790. Min Act: -0.0000

Data Index: 63936 (The Pile)

Max Activating Token Index: 875

Text #12

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2948. Min Act: -0.0000

Data Index: 880905 (The Pile)

Max Activating Token Index: 133

Text #13

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2638. Min Act: -0.0000

Data Index: 1696551 (The Pile)

Max Activating Token Index: 690

Text #14

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2686. Min Act: -0.0000

Data Index: 1445665 (The Pile)

Max Activating Token Index: 166

Text #15

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2814. Min Act: -0.0000

Data Index: 1989476 (The Pile)

Max Activating Token Index: 33

Text #16

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2856. Min Act: -0.0000

Data Index: 260279 (The Pile)

Max Activating Token Index: 227

Text #17

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2871. Min Act: -0.0000

Data Index: 78045 (The Pile)

Max Activating Token Index: 361

Text #18

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2770. Min Act: -0.0000

Data Index: 875926 (The Pile)

Max Activating Token Index: 935

Text #19

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.3060. Min Act: -0.0000

Data Index: 533319 (The Pile)

Max Activating Token Index: 415