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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3670 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.4474. Min Act: -0.0000

Data Index: 1043148 (C4 (Web Text))

Max Activating Token Index: 483

Text #1

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.4762. Min Act: -0.0000

Data Index: 547782 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.4269. Min Act: -0.0000

Data Index: 22055 (C4 (Web Text))

Max Activating Token Index: 386

Text #3

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.4954. Min Act: -0.0001

Data Index: 307688 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.4805. Min Act: -0.0000

Data Index: 1172281 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.3873. Min Act: -0.0001

Data Index: 204246 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.4251. Min Act: -0.0000

Data Index: 537732 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.4132. Min Act: -0.0001

Data Index: 509050 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.3690. Min Act: -0.0000

Data Index: 250451 (C4 (Web Text))

Max Activating Token Index: 159

Text #9

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.3709. Min Act: -0.0000

Data Index: 97277 (C4 (Web Text))

Max Activating Token Index: 273

Text #10

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.3855. Min Act: -0.0000

Data Index: 1281068 (C4 (Web Text))

Max Activating Token Index: 319

Text #11

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.3026. Min Act: -0.0001

Data Index: 893980 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.3359. Min Act: -0.0000

Data Index: 1210264 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.3228. Min Act: -0.0000

Data Index: 1272761 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.3279. Min Act: -0.0000

Data Index: 389123 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.2809. Min Act: -0.0000

Data Index: 16841 (C4 (Web Text))

Max Activating Token Index: 482

Text #16

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.3535. Min Act: -0.0000

Data Index: 266919 (C4 (Web Text))

Max Activating Token Index: 501

Text #17

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.3158. Min Act: -0.0000

Data Index: 580504 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.3079. Min Act: -0.0000

Data Index: 840318 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 1.4954. Min Range: -1.4954

Max Act: 1.2512. Min Act: -0.0001

Data Index: 216972 (C4 (Web Text))

Max Activating Token Index: 125