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

Dataset: Open Web Text

Neuron 173 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: 3.1286. Min Range: -3.1286

Max Act: 3.1286. Min Act: -0.1700

Data Index: 3509050 (Open Web Text)

Max Activating Token Index: 606

Text #1

Max Range: 3.1286. Min Range: -3.1286

Max Act: 3.0787. Min Act: -0.1700

Data Index: 1741584 (Open Web Text)

Max Activating Token Index: 849

Text #2

Max Range: 3.1286. Min Range: -3.1286

Max Act: 3.0644. Min Act: -0.1700

Data Index: 3554045 (Open Web Text)

Max Activating Token Index: 721

Text #3

Max Range: 3.1286. Min Range: -3.1286

Max Act: 3.0567. Min Act: -0.1700

Data Index: 4391761 (Open Web Text)

Max Activating Token Index: 131

Text #4

Max Range: 3.1286. Min Range: -3.1286

Max Act: 3.0384. Min Act: -0.1700

Data Index: 6417926 (Open Web Text)

Max Activating Token Index: 139

Text #5

Max Range: 3.1286. Min Range: -3.1286

Max Act: 3.0218. Min Act: -0.1700

Data Index: 8692828 (Open Web Text)

Max Activating Token Index: 227

Text #6

Max Range: 3.1286. Min Range: -3.1286

Max Act: 3.0140. Min Act: -0.1700

Data Index: 2168835 (Open Web Text)

Max Activating Token Index: 323

Text #7

Max Range: 3.1286. Min Range: -3.1286

Max Act: 3.0020. Min Act: -0.1700

Data Index: 2067530 (Open Web Text)

Max Activating Token Index: 504

Text #8

Max Range: 3.1286. Min Range: -3.1286

Max Act: 3.0066. Min Act: -0.1700

Data Index: 5918617 (Open Web Text)

Max Activating Token Index: 874

Text #9

Max Range: 3.1286. Min Range: -3.1286

Max Act: 3.0156. Min Act: -0.1700

Data Index: 1164041 (Open Web Text)

Max Activating Token Index: 152

Text #10

Max Range: 3.1286. Min Range: -3.1286

Max Act: 2.9906. Min Act: -0.1700

Data Index: 8275215 (Open Web Text)

Max Activating Token Index: 535

Text #11

Max Range: 3.1286. Min Range: -3.1286

Max Act: 2.9801. Min Act: -0.1700

Data Index: 750414 (Open Web Text)

Max Activating Token Index: 190

Text #12

Max Range: 3.1286. Min Range: -3.1286

Max Act: 2.9727. Min Act: -0.1700

Data Index: 1483046 (Open Web Text)

Max Activating Token Index: 337

Text #13

Max Range: 3.1286. Min Range: -3.1286

Max Act: 2.9420. Min Act: -0.1700

Data Index: 1647811 (Open Web Text)

Max Activating Token Index: 959

Text #14

Max Range: 3.1286. Min Range: -3.1286

Max Act: 2.9569. Min Act: -0.1700

Data Index: 6818217 (Open Web Text)

Max Activating Token Index: 513

Text #15

Max Range: 3.1286. Min Range: -3.1286

Max Act: 2.9515. Min Act: -0.1700

Data Index: 2302144 (Open Web Text)

Max Activating Token Index: 1012

Text #16

Max Range: 3.1286. Min Range: -3.1286

Max Act: 2.9560. Min Act: -0.1700

Data Index: 1998399 (Open Web Text)

Max Activating Token Index: 658

Text #17

Max Range: 3.1286. Min Range: -3.1286

Max Act: 2.9600. Min Act: -0.1700

Data Index: 5599263 (Open Web Text)

Max Activating Token Index: 212

Text #18

Max Range: 3.1286. Min Range: -3.1286

Max Act: 2.9480. Min Act: -0.1700

Data Index: 6792790 (Open Web Text)

Max Activating Token Index: 81

Text #19

Max Range: 3.1286. Min Range: -3.1286

Max Act: 2.9482. Min Act: -0.1700

Data Index: 8681762 (Open Web Text)

Max Activating Token Index: 341