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

Dataset: The Pile

Neuron 2998 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: 0.3316. Min Range: -0.3316

Max Act: 0.3143. Min Act: -0.0000

Data Index: 57069 (The Pile)

Max Activating Token Index: 927

Text #1

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.3316. Min Act: -0.0000

Data Index: 653609 (The Pile)

Max Activating Token Index: 67

Text #2

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.3146. Min Act: -0.0000

Data Index: 1089304 (The Pile)

Max Activating Token Index: 245

Text #3

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2902. Min Act: -0.0000

Data Index: 970064 (The Pile)

Max Activating Token Index: 693

Text #4

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2914. Min Act: -0.0000

Data Index: 986203 (The Pile)

Max Activating Token Index: 881

Text #5

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2872. Min Act: -0.0000

Data Index: 837605 (The Pile)

Max Activating Token Index: 146

Text #6

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2952. Min Act: -0.0000

Data Index: 303260 (The Pile)

Max Activating Token Index: 285

Text #7

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2868. Min Act: -0.0000

Data Index: 1306381 (The Pile)

Max Activating Token Index: 574

Text #8

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2947. Min Act: -0.0000

Data Index: 1764763 (The Pile)

Max Activating Token Index: 694

Text #9

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2671. Min Act: -0.0000

Data Index: 574172 (The Pile)

Max Activating Token Index: 763

Text #10

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2938. Min Act: -0.0000

Data Index: 519651 (The Pile)

Max Activating Token Index: 414

Text #11

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2596. Min Act: -0.0000

Data Index: 27692 (The Pile)

Max Activating Token Index: 983

Text #12

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2651. Min Act: -0.0000

Data Index: 1704680 (The Pile)

Max Activating Token Index: 268

Text #13

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2632. Min Act: -0.0000

Data Index: 644831 (The Pile)

Max Activating Token Index: 173

Text #14

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2972. Min Act: -0.0000

Data Index: 1781942 (The Pile)

Max Activating Token Index: 219

Text #15

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2429. Min Act: -0.0000

Data Index: 1731755 (The Pile)

Max Activating Token Index: 231

Text #16

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2535. Min Act: -0.0000

Data Index: 1784164 (The Pile)

Max Activating Token Index: 192

Text #17

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2602. Min Act: -0.0000

Data Index: 204434 (The Pile)

Max Activating Token Index: 70

Text #18

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2503. Min Act: -0.0000

Data Index: 1494556 (The Pile)

Max Activating Token Index: 688

Text #19

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2495. Min Act: -0.0000

Data Index: 1127003 (The Pile)

Max Activating Token Index: 66