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

Dataset: The Pile

Neuron 999 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6958. Min Range: -3.6958

Max Act: 3.5968. Min Act: -0.0000

Data Index: 307568 (The Pile)

Max Activating Token Index: 738

Text #1

Max Range: 3.6958. Min Range: -3.6958

Max Act: 3.6767. Min Act: -0.0000

Data Index: 141054 (The Pile)

Max Activating Token Index: 441

Text #2

Max Range: 3.6958. Min Range: -3.6958

Max Act: 3.5976. Min Act: -0.0000

Data Index: 1306213 (The Pile)

Max Activating Token Index: 235

Text #3

Max Range: 3.6958. Min Range: -3.6958

Max Act: 3.6958. Min Act: -0.0000

Data Index: 407608 (The Pile)

Max Activating Token Index: 42

Text #4

Max Range: 3.6958. Min Range: -3.6958

Max Act: 3.4676. Min Act: -0.0000

Data Index: 702030 (The Pile)

Max Activating Token Index: 142

Text #5

Max Range: 3.6958. Min Range: -3.6958

Max Act: 3.4516. Min Act: -0.0000

Data Index: 1633539 (The Pile)

Max Activating Token Index: 237

Text #6

Max Range: 3.6958. Min Range: -3.6958

Max Act: 3.3232. Min Act: -0.0000

Data Index: 1878602 (The Pile)

Max Activating Token Index: 70

Text #7

Max Range: 3.6958. Min Range: -3.6958

Max Act: 3.0066. Min Act: -0.0000

Data Index: 898196 (The Pile)

Max Activating Token Index: 674

Text #8

Max Range: 3.6958. Min Range: -3.6958

Max Act: 3.2725. Min Act: -0.0000

Data Index: 1419347 (The Pile)

Max Activating Token Index: 358

Text #9

Max Range: 3.6958. Min Range: -3.6958

Max Act: 3.2566. Min Act: -0.0000

Data Index: 1079543 (The Pile)

Max Activating Token Index: 21

Text #10

Max Range: 3.6958. Min Range: -3.6958

Max Act: 3.0657. Min Act: -0.0000

Data Index: 152028 (The Pile)

Max Activating Token Index: 129

Text #11

Max Range: 3.6958. Min Range: -3.6958

Max Act: 3.3733. Min Act: -0.0000

Data Index: 1205896 (The Pile)

Max Activating Token Index: 204

Text #12

Max Range: 3.6958. Min Range: -3.6958

Max Act: 3.1945. Min Act: -0.0000

Data Index: 74234 (The Pile)

Max Activating Token Index: 951

Text #13

Max Range: 3.6958. Min Range: -3.6958

Max Act: 3.1943. Min Act: -0.0000

Data Index: 580384 (The Pile)

Max Activating Token Index: 87

Text #14

Max Range: 3.6958. Min Range: -3.6958

Max Act: 2.8789. Min Act: -0.0000

Data Index: 671541 (The Pile)

Max Activating Token Index: 901

Text #15

Max Range: 3.6958. Min Range: -3.6958

Max Act: 3.2158. Min Act: -0.0000

Data Index: 1347624 (The Pile)

Max Activating Token Index: 761

Text #16

Max Range: 3.6958. Min Range: -3.6958

Max Act: 3.0432. Min Act: -0.0000

Data Index: 1787539 (The Pile)

Max Activating Token Index: 581

Text #17

Max Range: 3.6958. Min Range: -3.6958

Max Act: 3.1777. Min Act: -0.0000

Data Index: 1319153 (The Pile)

Max Activating Token Index: 129

Text #18

Max Range: 3.6958. Min Range: -3.6958

Max Act: 3.1571. Min Act: -0.0000

Data Index: 1600253 (The Pile)

Max Activating Token Index: 792

Text #19

Max Range: 3.6958. Min Range: -3.6958

Max Act: 3.1789. Min Act: -0.0000

Data Index: 1080742 (The Pile)

Max Activating Token Index: 216