Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1151 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.5787. Min Act: -0.1700

Data Index: 1193066 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.3907. Min Act: -0.1700

Data Index: 472128 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.3750. Min Act: -0.1700

Data Index: 1305283 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.3593. Min Act: -0.1700

Data Index: 325557 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.3750. Min Act: -0.1700

Data Index: 186082 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.3436. Min Act: -0.1700

Data Index: 1318806 (C4 (Web Text))

Max Activating Token Index: 717

Text #6

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.3750. Min Act: -0.1700

Data Index: 898355 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.3279. Min Act: -0.1700

Data Index: 261758 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.2965. Min Act: -0.1700

Data Index: 625924 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.2965. Min Act: -0.1700

Data Index: 527831 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.2965. Min Act: -0.1700

Data Index: 235871 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.2651. Min Act: -0.1700

Data Index: 613215 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.3279. Min Act: -0.1700

Data Index: 567111 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.2651. Min Act: -0.1700

Data Index: 627286 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.2494. Min Act: -0.1700

Data Index: 50568 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.2808. Min Act: -0.1700

Data Index: 1001755 (C4 (Web Text))

Max Activating Token Index: 449

Text #16

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.1864. Min Act: -0.1700

Data Index: 374826 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.2336. Min Act: -0.1700

Data Index: 700820 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.2022. Min Act: -0.1700

Data Index: 758268 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.1864. Min Act: -0.1700

Data Index: 1122849 (C4 (Web Text))

Max Activating Token Index: 559