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

Dataset: The Pile

Neuron 1253 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6437. Min Range: -1.6437

Max Act: 1.6437. Min Act: -0.0000

Data Index: 893137 (The Pile)

Max Activating Token Index: 123

Text #1

Max Range: 1.6437. Min Range: -1.6437

Max Act: 1.6395. Min Act: -0.0000

Data Index: 1017692 (The Pile)

Max Activating Token Index: 334

Text #2

Max Range: 1.6437. Min Range: -1.6437

Max Act: 1.5872. Min Act: -0.0000

Data Index: 1341909 (The Pile)

Max Activating Token Index: 605

Text #3

Max Range: 1.6437. Min Range: -1.6437

Max Act: 1.5903. Min Act: -0.0000

Data Index: 1680220 (The Pile)

Max Activating Token Index: 107

Text #4

Max Range: 1.6437. Min Range: -1.6437

Max Act: 1.4585. Min Act: -0.0000

Data Index: 826593 (The Pile)

Max Activating Token Index: 148

Text #5

Max Range: 1.6437. Min Range: -1.6437

Max Act: 1.5341. Min Act: -0.0000

Data Index: 169425 (The Pile)

Max Activating Token Index: 106

Text #6

Max Range: 1.6437. Min Range: -1.6437

Max Act: 1.4911. Min Act: -0.0000

Data Index: 764783 (The Pile)

Max Activating Token Index: 193

Text #7

Max Range: 1.6437. Min Range: -1.6437

Max Act: 1.5010. Min Act: -0.0000

Data Index: 1939311 (The Pile)

Max Activating Token Index: 236

Text #8

Max Range: 1.6437. Min Range: -1.6437

Max Act: 1.4189. Min Act: -0.0000

Data Index: 24779 (The Pile)

Max Activating Token Index: 441

Text #9

Max Range: 1.6437. Min Range: -1.6437

Max Act: 1.4193. Min Act: -0.0000

Data Index: 1719118 (The Pile)

Max Activating Token Index: 368

Text #10

Max Range: 1.6437. Min Range: -1.6437

Max Act: 1.4188. Min Act: -0.0000

Data Index: 1393363 (The Pile)

Max Activating Token Index: 300

Text #11

Max Range: 1.6437. Min Range: -1.6437

Max Act: 1.4957. Min Act: -0.0000

Data Index: 92551 (The Pile)

Max Activating Token Index: 135

Text #12

Max Range: 1.6437. Min Range: -1.6437

Max Act: 1.3224. Min Act: -0.0000

Data Index: 1147792 (The Pile)

Max Activating Token Index: 92

Text #13

Max Range: 1.6437. Min Range: -1.6437

Max Act: 1.3427. Min Act: -0.0000

Data Index: 143863 (The Pile)

Max Activating Token Index: 142

Text #14

Max Range: 1.6437. Min Range: -1.6437

Max Act: 1.4227. Min Act: -0.0000

Data Index: 821980 (The Pile)

Max Activating Token Index: 247

Text #15

Max Range: 1.6437. Min Range: -1.6437

Max Act: 1.3729. Min Act: -0.0000

Data Index: 790316 (The Pile)

Max Activating Token Index: 189

Text #16

Max Range: 1.6437. Min Range: -1.6437

Max Act: 1.2890. Min Act: -0.0000

Data Index: 35574 (The Pile)

Max Activating Token Index: 204

Text #17

Max Range: 1.6437. Min Range: -1.6437

Max Act: 1.3617. Min Act: -0.0000

Data Index: 1273094 (The Pile)

Max Activating Token Index: 267

Text #18

Max Range: 1.6437. Min Range: -1.6437

Max Act: 1.3175. Min Act: -0.0000

Data Index: 1834299 (The Pile)

Max Activating Token Index: 153

Text #19

Max Range: 1.6437. Min Range: -1.6437

Max Act: 1.3494. Min Act: -0.0000

Data Index: 1914769 (The Pile)

Max Activating Token Index: 298