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

Dataset: The Pile

Neuron 1299 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9547. Min Range: -3.9547

Max Act: 3.9547. Min Act: -0.0000

Data Index: 649377 (The Pile)

Max Activating Token Index: 586

Text #1

Max Range: 3.9547. Min Range: -3.9547

Max Act: 3.2913. Min Act: -0.0000

Data Index: 64020 (The Pile)

Max Activating Token Index: 559

Text #2

Max Range: 3.9547. Min Range: -3.9547

Max Act: 2.6984. Min Act: -0.0000

Data Index: 1147028 (The Pile)

Max Activating Token Index: 232

Text #3

Max Range: 3.9547. Min Range: -3.9547

Max Act: 2.6082. Min Act: -0.0000

Data Index: 980161 (The Pile)

Max Activating Token Index: 257

Text #4

Max Range: 3.9547. Min Range: -3.9547

Max Act: 2.6043. Min Act: -0.0000

Data Index: 1320181 (The Pile)

Max Activating Token Index: 983

Text #5

Max Range: 3.9547. Min Range: -3.9547

Max Act: 2.5452. Min Act: -0.0000

Data Index: 1487155 (The Pile)

Max Activating Token Index: 276

Text #6

Max Range: 3.9547. Min Range: -3.9547

Max Act: 2.5314. Min Act: -0.0000

Data Index: 497233 (The Pile)

Max Activating Token Index: 184

Text #7

Max Range: 3.9547. Min Range: -3.9547

Max Act: 2.4007. Min Act: -0.0000

Data Index: 1122667 (The Pile)

Max Activating Token Index: 935

Text #8

Max Range: 3.9547. Min Range: -3.9547

Max Act: 2.3543. Min Act: -0.0000

Data Index: 1511259 (The Pile)

Max Activating Token Index: 415

Text #9

Max Range: 3.9547. Min Range: -3.9547

Max Act: 2.4408. Min Act: -0.0000

Data Index: 837534 (The Pile)

Max Activating Token Index: 484

Text #10

Max Range: 3.9547. Min Range: -3.9547

Max Act: 2.4336. Min Act: -0.0000

Data Index: 1392525 (The Pile)

Max Activating Token Index: 154

Text #11

Max Range: 3.9547. Min Range: -3.9547

Max Act: 2.4019. Min Act: -0.0000

Data Index: 171455 (The Pile)

Max Activating Token Index: 727

Text #12

Max Range: 3.9547. Min Range: -3.9547

Max Act: 2.4249. Min Act: -0.0000

Data Index: 1605799 (The Pile)

Max Activating Token Index: 24

Text #13

Max Range: 3.9547. Min Range: -3.9547

Max Act: 2.5279. Min Act: -0.0000

Data Index: 214110 (The Pile)

Max Activating Token Index: 633

Text #14

Max Range: 3.9547. Min Range: -3.9547

Max Act: 2.3908. Min Act: -0.0000

Data Index: 1564530 (The Pile)

Max Activating Token Index: 334

Text #15

Max Range: 3.9547. Min Range: -3.9547

Max Act: 2.3998. Min Act: -0.0000

Data Index: 1576628 (The Pile)

Max Activating Token Index: 181

Text #16

Max Range: 3.9547. Min Range: -3.9547

Max Act: 2.5129. Min Act: -0.0000

Data Index: 226551 (The Pile)

Max Activating Token Index: 278

Text #17

Max Range: 3.9547. Min Range: -3.9547

Max Act: 2.3694. Min Act: -0.0000

Data Index: 1887742 (The Pile)

Max Activating Token Index: 189

Text #18

Max Range: 3.9547. Min Range: -3.9547

Max Act: 2.3637. Min Act: 0.0000

Data Index: 1710245 (The Pile)

Max Activating Token Index: 44

Text #19

Max Range: 3.9547. Min Range: -3.9547

Max Act: 2.2564. Min Act: -0.0000

Data Index: 700760 (The Pile)

Max Activating Token Index: 401