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

Dataset: The Pile

Neuron 3350 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: 0.6485. Min Range: -0.6485

Max Act: 0.6485. Min Act: -0.0000

Data Index: 1676736 (The Pile)

Max Activating Token Index: 159

Text #1

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.6147. Min Act: -0.0000

Data Index: 28234 (The Pile)

Max Activating Token Index: 659

Text #2

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.5154. Min Act: -0.0000

Data Index: 35507 (The Pile)

Max Activating Token Index: 299

Text #3

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4943. Min Act: -0.0000

Data Index: 1091069 (The Pile)

Max Activating Token Index: 276

Text #4

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4745. Min Act: -0.0000

Data Index: 433030 (The Pile)

Max Activating Token Index: 271

Text #5

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4426. Min Act: -0.0000

Data Index: 468313 (The Pile)

Max Activating Token Index: 207

Text #6

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4739. Min Act: -0.0000

Data Index: 1251100 (The Pile)

Max Activating Token Index: 455

Text #7

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4536. Min Act: -0.0000

Data Index: 886956 (The Pile)

Max Activating Token Index: 76

Text #8

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4358. Min Act: -0.0000

Data Index: 714827 (The Pile)

Max Activating Token Index: 242

Text #9

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4186. Min Act: -0.0000

Data Index: 1619359 (The Pile)

Max Activating Token Index: 525

Text #10

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4082. Min Act: -0.0000

Data Index: 1876882 (The Pile)

Max Activating Token Index: 488

Text #11

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.3946. Min Act: -0.0000

Data Index: 763595 (The Pile)

Max Activating Token Index: 54

Text #12

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4501. Min Act: -0.0000

Data Index: 158651 (The Pile)

Max Activating Token Index: 354

Text #13

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.3954. Min Act: -0.0000

Data Index: 1737520 (The Pile)

Max Activating Token Index: 514

Text #14

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4073. Min Act: -0.0000

Data Index: 486033 (The Pile)

Max Activating Token Index: 190

Text #15

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.3925. Min Act: -0.0000

Data Index: 1207742 (The Pile)

Max Activating Token Index: 989

Text #16

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4078. Min Act: -0.0000

Data Index: 148337 (The Pile)

Max Activating Token Index: 443

Text #17

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.3914. Min Act: -0.0000

Data Index: 1725887 (The Pile)

Max Activating Token Index: 617

Text #18

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.3786. Min Act: -0.0000

Data Index: 895615 (The Pile)

Max Activating Token Index: 216

Text #19

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.3886. Min Act: -0.0000

Data Index: 1422479 (The Pile)

Max Activating Token Index: 387