Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 24 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.8047. Min Range: -3.8047

Max Act: 3.7885. Min Act: -0.1700

Data Index: 5368780 (Open Web Text)

Max Activating Token Index: 199

Text #1

Max Range: 3.8047. Min Range: -3.8047

Max Act: 3.8047. Min Act: -0.1700

Data Index: 8319557 (Open Web Text)

Max Activating Token Index: 106

Text #2

Max Range: 3.8047. Min Range: -3.8047

Max Act: 3.7635. Min Act: -0.1700

Data Index: 1253318 (Open Web Text)

Max Activating Token Index: 111

Text #3

Max Range: 3.8047. Min Range: -3.8047

Max Act: 3.7682. Min Act: -0.1700

Data Index: 4257038 (Open Web Text)

Max Activating Token Index: 154

Text #4

Max Range: 3.8047. Min Range: -3.8047

Max Act: 3.7706. Min Act: -0.1700

Data Index: 7671701 (Open Web Text)

Max Activating Token Index: 88

Text #5

Max Range: 3.8047. Min Range: -3.8047

Max Act: 3.7640. Min Act: -0.1700

Data Index: 7775371 (Open Web Text)

Max Activating Token Index: 347

Text #6

Max Range: 3.8047. Min Range: -3.8047

Max Act: 3.7330. Min Act: -0.1700

Data Index: 3080804 (Open Web Text)

Max Activating Token Index: 575

Text #7

Max Range: 3.8047. Min Range: -3.8047

Max Act: 3.7251. Min Act: -0.1700

Data Index: 2578437 (Open Web Text)

Max Activating Token Index: 163

Text #8

Max Range: 3.8047. Min Range: -3.8047

Max Act: 3.7359. Min Act: -0.1700

Data Index: 2578438 (Open Web Text)

Max Activating Token Index: 237

Text #9

Max Range: 3.8047. Min Range: -3.8047

Max Act: 3.7404. Min Act: -0.1700

Data Index: 3362648 (Open Web Text)

Max Activating Token Index: 133

Text #10

Max Range: 3.8047. Min Range: -3.8047

Max Act: 3.7285. Min Act: -0.1700

Data Index: 2324018 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 3.8047. Min Range: -3.8047

Max Act: 3.7431. Min Act: -0.1700

Data Index: 8162575 (Open Web Text)

Max Activating Token Index: 511

Text #12

Max Range: 3.8047. Min Range: -3.8047

Max Act: 3.7213. Min Act: -0.1700

Data Index: 252107 (Open Web Text)

Max Activating Token Index: 474

Text #13

Max Range: 3.8047. Min Range: -3.8047

Max Act: 3.7271. Min Act: -0.1700

Data Index: 6451630 (Open Web Text)

Max Activating Token Index: 559

Text #14

Max Range: 3.8047. Min Range: -3.8047

Max Act: 3.7340. Min Act: -0.1700

Data Index: 3894111 (Open Web Text)

Max Activating Token Index: 340

Text #15

Max Range: 3.8047. Min Range: -3.8047

Max Act: 3.7282. Min Act: -0.1700

Data Index: 5077805 (Open Web Text)

Max Activating Token Index: 277

Text #16

Max Range: 3.8047. Min Range: -3.8047

Max Act: 3.7048. Min Act: -0.1700

Data Index: 623403 (Open Web Text)

Max Activating Token Index: 649

Text #17

Max Range: 3.8047. Min Range: -3.8047

Max Act: 3.7183. Min Act: -0.1700

Data Index: 2324017 (Open Web Text)

Max Activating Token Index: 208

Text #18

Max Range: 3.8047. Min Range: -3.8047

Max Act: 3.7059. Min Act: -0.1700

Data Index: 892848 (Open Web Text)

Max Activating Token Index: 53

Text #19

Max Range: 3.8047. Min Range: -3.8047

Max Act: 3.7150. Min Act: -0.1700

Data Index: 4876437 (Open Web Text)

Max Activating Token Index: 554