Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1246 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.5179. Min Range: -3.5179

Max Act: 3.5179. Min Act: -0.1700

Data Index: 293564 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 3.5179. Min Range: -3.5179

Max Act: 3.4239. Min Act: -0.1700

Data Index: 673279 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 3.5179. Min Range: -3.5179

Max Act: 3.3454. Min Act: -0.1700

Data Index: 253878 (C4 (Web Text))

Max Activating Token Index: 574

Text #3

Max Range: 3.5179. Min Range: -3.5179

Max Act: 3.2983. Min Act: -0.1700

Data Index: 799063 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 3.5179. Min Range: -3.5179

Max Act: 3.3140. Min Act: -0.1700

Data Index: 48584 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 3.5179. Min Range: -3.5179

Max Act: 3.2826. Min Act: -0.1700

Data Index: 23174 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 3.5179. Min Range: -3.5179

Max Act: 3.2826. Min Act: -0.1700

Data Index: 737337 (C4 (Web Text))

Max Activating Token Index: 522

Text #7

Max Range: 3.5179. Min Range: -3.5179

Max Act: 3.2669. Min Act: -0.1700

Data Index: 285240 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 3.5179. Min Range: -3.5179

Max Act: 3.2983. Min Act: -0.1700

Data Index: 549891 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 3.5179. Min Range: -3.5179

Max Act: 3.2983. Min Act: -0.1700

Data Index: 1080363 (C4 (Web Text))

Max Activating Token Index: 791

Text #10

Max Range: 3.5179. Min Range: -3.5179

Max Act: 3.2512. Min Act: -0.1700

Data Index: 1351168 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 3.5179. Min Range: -3.5179

Max Act: 3.2512. Min Act: -0.1700

Data Index: 507271 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 3.5179. Min Range: -3.5179

Max Act: 3.2512. Min Act: -0.1700

Data Index: 952218 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 3.5179. Min Range: -3.5179

Max Act: 3.2040. Min Act: -0.1700

Data Index: 857131 (C4 (Web Text))

Max Activating Token Index: 626

Text #14

Max Range: 3.5179. Min Range: -3.5179

Max Act: 3.2197. Min Act: -0.1700

Data Index: 969206 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 3.5179. Min Range: -3.5179

Max Act: 3.2512. Min Act: -0.1700

Data Index: 432709 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 3.5179. Min Range: -3.5179

Max Act: 3.2355. Min Act: -0.1700

Data Index: 360998 (C4 (Web Text))

Max Activating Token Index: 639

Text #17

Max Range: 3.5179. Min Range: -3.5179

Max Act: 3.2355. Min Act: -0.1700

Data Index: 1112176 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 3.5179. Min Range: -3.5179

Max Act: 3.1883. Min Act: -0.1700

Data Index: 1083134 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 3.5179. Min Range: -3.5179

Max Act: 3.2040. Min Act: -0.1700

Data Index: 562199 (C4 (Web Text))

Max Activating Token Index: 279