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

Dataset: The Pile

Neuron 1452 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: 0.8246. Min Range: -0.8246

Max Act: 0.8246. Min Act: -0.0000

Data Index: 1910589 (The Pile)

Max Activating Token Index: 644

Text #1

Max Range: 0.8246. Min Range: -0.8246

Max Act: 0.6760. Min Act: -0.0000

Data Index: 1927853 (The Pile)

Max Activating Token Index: 793

Text #2

Max Range: 0.8246. Min Range: -0.8246

Max Act: 0.6431. Min Act: -0.0000

Data Index: 1769312 (The Pile)

Max Activating Token Index: 952

Text #3

Max Range: 0.8246. Min Range: -0.8246

Max Act: 0.6326. Min Act: -0.0000

Data Index: 791589 (The Pile)

Max Activating Token Index: 133

Text #4

Max Range: 0.8246. Min Range: -0.8246

Max Act: 0.6457. Min Act: -0.0000

Data Index: 1505377 (The Pile)

Max Activating Token Index: 227

Text #5

Max Range: 0.8246. Min Range: -0.8246

Max Act: 0.5982. Min Act: -0.0000

Data Index: 1439455 (The Pile)

Max Activating Token Index: 857

Text #6

Max Range: 0.8246. Min Range: -0.8246

Max Act: 0.6151. Min Act: -0.0000

Data Index: 927686 (The Pile)

Max Activating Token Index: 384

Text #7

Max Range: 0.8246. Min Range: -0.8246

Max Act: 0.6054. Min Act: -0.0000

Data Index: 977168 (The Pile)

Max Activating Token Index: 120

Text #8

Max Range: 0.8246. Min Range: -0.8246

Max Act: 0.6197. Min Act: -0.0000

Data Index: 387567 (The Pile)

Max Activating Token Index: 931

Text #9

Max Range: 0.8246. Min Range: -0.8246

Max Act: 0.5599. Min Act: -0.0000

Data Index: 922316 (The Pile)

Max Activating Token Index: 1020

Text #10

Max Range: 0.8246. Min Range: -0.8246

Max Act: 0.5703. Min Act: -0.0000

Data Index: 1211209 (The Pile)

Max Activating Token Index: 73

Text #11

Max Range: 0.8246. Min Range: -0.8246

Max Act: 0.5831. Min Act: -0.0000

Data Index: 488419 (The Pile)

Max Activating Token Index: 174

Text #12

Max Range: 0.8246. Min Range: -0.8246

Max Act: 0.5547. Min Act: -0.0000

Data Index: 734736 (The Pile)

Max Activating Token Index: 365

Text #13

Max Range: 0.8246. Min Range: -0.8246

Max Act: 0.5859. Min Act: -0.0000

Data Index: 101667 (The Pile)

Max Activating Token Index: 965

Text #14

Max Range: 0.8246. Min Range: -0.8246

Max Act: 0.5461. Min Act: -0.0000

Data Index: 749694 (The Pile)

Max Activating Token Index: 406

Text #15

Max Range: 0.8246. Min Range: -0.8246

Max Act: 0.4953. Min Act: -0.0000

Data Index: 735161 (The Pile)

Max Activating Token Index: 635

Text #16

Max Range: 0.8246. Min Range: -0.8246

Max Act: 0.5534. Min Act: -0.0000

Data Index: 335740 (The Pile)

Max Activating Token Index: 1001

Text #17

Max Range: 0.8246. Min Range: -0.8246

Max Act: 0.5180. Min Act: -0.0000

Data Index: 367867 (The Pile)

Max Activating Token Index: 276

Text #18

Max Range: 0.8246. Min Range: -0.8246

Max Act: 0.5320. Min Act: -0.0000

Data Index: 245727 (The Pile)

Max Activating Token Index: 841

Text #19

Max Range: 0.8246. Min Range: -0.8246

Max Act: 0.5311. Min Act: -0.0000

Data Index: 1305498 (The Pile)

Max Activating Token Index: 896