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

Dataset: Open Web Text

Neuron 2929 in Layer 3

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: 3.2584. Min Range: -3.2584

Max Act: 3.2236. Min Act: -0.1700

Data Index: 5474703 (Open Web Text)

Max Activating Token Index: 466

Text #1

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.2584. Min Act: -0.1700

Data Index: 2348670 (Open Web Text)

Max Activating Token Index: 412

Text #2

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.1555. Min Act: -0.1700

Data Index: 3835299 (Open Web Text)

Max Activating Token Index: 169

Text #3

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.1324. Min Act: -0.1700

Data Index: 7310023 (Open Web Text)

Max Activating Token Index: 236

Text #4

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.1190. Min Act: -0.1700

Data Index: 8536164 (Open Web Text)

Max Activating Token Index: 553

Text #5

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.1264. Min Act: -0.1700

Data Index: 3728548 (Open Web Text)

Max Activating Token Index: 391

Text #6

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.0714. Min Act: -0.1700

Data Index: 4476920 (Open Web Text)

Max Activating Token Index: 935

Text #7

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.1067. Min Act: -0.1700

Data Index: 397276 (Open Web Text)

Max Activating Token Index: 133

Text #8

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.1096. Min Act: -0.1700

Data Index: 148242 (Open Web Text)

Max Activating Token Index: 149

Text #9

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.0946. Min Act: -0.1700

Data Index: 4231645 (Open Web Text)

Max Activating Token Index: 511

Text #10

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.1122. Min Act: -0.1700

Data Index: 4189488 (Open Web Text)

Max Activating Token Index: 642

Text #11

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.0830. Min Act: -0.1700

Data Index: 2663751 (Open Web Text)

Max Activating Token Index: 159

Text #12

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.0869. Min Act: -0.1700

Data Index: 4004986 (Open Web Text)

Max Activating Token Index: 249

Text #13

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.0338. Min Act: -0.1700

Data Index: 1618040 (Open Web Text)

Max Activating Token Index: 750

Text #14

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.1209. Min Act: -0.1700

Data Index: 60628 (Open Web Text)

Max Activating Token Index: 760

Text #15

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.0694. Min Act: -0.1700

Data Index: 1578967 (Open Web Text)

Max Activating Token Index: 471

Text #16

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.0228. Min Act: -0.1700

Data Index: 8668956 (Open Web Text)

Max Activating Token Index: 210

Text #17

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.0791. Min Act: -0.1700

Data Index: 4057576 (Open Web Text)

Max Activating Token Index: 622

Text #18

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.0285. Min Act: -0.1700

Data Index: 5716245 (Open Web Text)

Max Activating Token Index: 169

Text #19

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.0559. Min Act: -0.1700

Data Index: 5852183 (Open Web Text)

Max Activating Token Index: 852