Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3764 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.3441. Min Act: -0.0000

Data Index: 1413673 (The Pile)

Max Activating Token Index: 369

Text #1

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.2942. Min Act: -0.0000

Data Index: 758734 (The Pile)

Max Activating Token Index: 970

Text #2

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.3061. Min Act: -0.0000

Data Index: 832605 (The Pile)

Max Activating Token Index: 540

Text #3

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.2936. Min Act: -0.0000

Data Index: 127647 (The Pile)

Max Activating Token Index: 258

Text #4

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.2701. Min Act: -0.0000

Data Index: 613461 (The Pile)

Max Activating Token Index: 566

Text #5

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.2719. Min Act: -0.0000

Data Index: 710300 (The Pile)

Max Activating Token Index: 964

Text #6

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.2693. Min Act: -0.0000

Data Index: 384302 (The Pile)

Max Activating Token Index: 546

Text #7

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.2619. Min Act: -0.0000

Data Index: 1558174 (The Pile)

Max Activating Token Index: 325

Text #8

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.2384. Min Act: -0.0000

Data Index: 198383 (The Pile)

Max Activating Token Index: 476

Text #9

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.2397. Min Act: -0.0000

Data Index: 1940916 (The Pile)

Max Activating Token Index: 576

Text #10

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.2340. Min Act: -0.0000

Data Index: 1538680 (The Pile)

Max Activating Token Index: 281

Text #11

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.2543. Min Act: -0.0000

Data Index: 1072334 (The Pile)

Max Activating Token Index: 576

Text #12

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.2700. Min Act: -0.0000

Data Index: 1944879 (The Pile)

Max Activating Token Index: 166

Text #13

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.2208. Min Act: -0.0000

Data Index: 1376389 (The Pile)

Max Activating Token Index: 173

Text #14

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.2426. Min Act: -0.0000

Data Index: 1755003 (The Pile)

Max Activating Token Index: 355

Text #15

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.2328. Min Act: -0.0000

Data Index: 348745 (The Pile)

Max Activating Token Index: 176

Text #16

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.2585. Min Act: -0.0000

Data Index: 1820963 (The Pile)

Max Activating Token Index: 619

Text #17

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.2341. Min Act: -0.0000

Data Index: 1207501 (The Pile)

Max Activating Token Index: 386

Text #18

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.2495. Min Act: -0.0000

Data Index: 1119384 (The Pile)

Max Activating Token Index: 114

Text #19

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.2277. Min Act: -0.0000

Data Index: 1073363 (The Pile)

Max Activating Token Index: 683