Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1689 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.4942. Min Range: -3.4942

Max Act: 3.4942. Min Act: -0.1700

Data Index: 720861 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 3.4942. Min Range: -3.4942

Max Act: 3.4001. Min Act: -0.1700

Data Index: 957542 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 3.4942. Min Range: -3.4942

Max Act: 3.3844. Min Act: -0.1700

Data Index: 450937 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 3.4942. Min Range: -3.4942

Max Act: 3.4001. Min Act: -0.1700

Data Index: 169344 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 3.4942. Min Range: -3.4942

Max Act: 3.3373. Min Act: -0.1700

Data Index: 163913 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 3.4942. Min Range: -3.4942

Max Act: 3.3373. Min Act: -0.1700

Data Index: 115573 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 3.4942. Min Range: -3.4942

Max Act: 3.3216. Min Act: -0.1700

Data Index: 355811 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 3.4942. Min Range: -3.4942

Max Act: 3.3059. Min Act: -0.1700

Data Index: 436250 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 3.4942. Min Range: -3.4942

Max Act: 3.3059. Min Act: -0.1700

Data Index: 215365 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 3.4942. Min Range: -3.4942

Max Act: 3.3216. Min Act: -0.1700

Data Index: 293320 (C4 (Web Text))

Max Activating Token Index: 675

Text #10

Max Range: 3.4942. Min Range: -3.4942

Max Act: 3.3059. Min Act: -0.1700

Data Index: 962027 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 3.4942. Min Range: -3.4942

Max Act: 3.3059. Min Act: -0.1700

Data Index: 318071 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 3.4942. Min Range: -3.4942

Max Act: 3.2902. Min Act: -0.1700

Data Index: 1524025 (Python Code)

Max Activating Token Index: 47

Text #13

Max Range: 3.4942. Min Range: -3.4942

Max Act: 3.2588. Min Act: -0.1700

Data Index: 269562 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 3.4942. Min Range: -3.4942

Max Act: 3.2588. Min Act: -0.1700

Data Index: 1625726 (Python Code)

Max Activating Token Index: 406

Text #15

Max Range: 3.4942. Min Range: -3.4942

Max Act: 3.2431. Min Act: -0.1700

Data Index: 772910 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 3.4942. Min Range: -3.4942

Max Act: 3.2431. Min Act: -0.1700

Data Index: 1302983 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 3.4942. Min Range: -3.4942

Max Act: 3.2431. Min Act: -0.1700

Data Index: 597390 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 3.4942. Min Range: -3.4942

Max Act: 3.2431. Min Act: -0.1700

Data Index: 597349 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 3.4942. Min Range: -3.4942

Max Act: 3.2431. Min Act: -0.1700

Data Index: 66864 (C4 (Web Text))

Max Activating Token Index: 482