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

Dataset: Open Web Text

Neuron 2142 in Layer 6

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: 11.3943. Min Range: -11.3943

Max Act: 11.3943. Min Act: -0.1700

Data Index: 6602869 (Open Web Text)

Max Activating Token Index: 428

Text #1

Max Range: 11.3943. Min Range: -11.3943

Max Act: 10.9692. Min Act: -0.1700

Data Index: 6009173 (Open Web Text)

Max Activating Token Index: 117

Text #2

Max Range: 11.3943. Min Range: -11.3943

Max Act: 10.9231. Min Act: -0.1700

Data Index: 3583852 (Open Web Text)

Max Activating Token Index: 166

Text #3

Max Range: 11.3943. Min Range: -11.3943

Max Act: 10.9047. Min Act: -0.1700

Data Index: 1155593 (Open Web Text)

Max Activating Token Index: 536

Text #4

Max Range: 11.3943. Min Range: -11.3943

Max Act: 10.8573. Min Act: -0.1700

Data Index: 4725382 (Open Web Text)

Max Activating Token Index: 154

Text #5

Max Range: 11.3943. Min Range: -11.3943

Max Act: 10.8888. Min Act: -0.1700

Data Index: 5673683 (Open Web Text)

Max Activating Token Index: 389

Text #6

Max Range: 11.3943. Min Range: -11.3943

Max Act: 10.7472. Min Act: -0.1700

Data Index: 8566241 (Open Web Text)

Max Activating Token Index: 453

Text #7

Max Range: 11.3943. Min Range: -11.3943

Max Act: 10.7195. Min Act: -0.1700

Data Index: 5550889 (Open Web Text)

Max Activating Token Index: 938

Text #8

Max Range: 11.3943. Min Range: -11.3943

Max Act: 10.9250. Min Act: -0.1700

Data Index: 2464351 (Open Web Text)

Max Activating Token Index: 527

Text #9

Max Range: 11.3943. Min Range: -11.3943

Max Act: 10.5872. Min Act: -0.1700

Data Index: 6518648 (Open Web Text)

Max Activating Token Index: 937

Text #10

Max Range: 11.3943. Min Range: -11.3943

Max Act: 10.4532. Min Act: -0.1700

Data Index: 4164808 (Open Web Text)

Max Activating Token Index: 300

Text #11

Max Range: 11.3943. Min Range: -11.3943

Max Act: 10.4440. Min Act: -0.1700

Data Index: 2099972 (Open Web Text)

Max Activating Token Index: 597

Text #12

Max Range: 11.3943. Min Range: -11.3943

Max Act: 10.3276. Min Act: -0.1700

Data Index: 1767087 (Open Web Text)

Max Activating Token Index: 723

Text #13

Max Range: 11.3943. Min Range: -11.3943

Max Act: 10.2071. Min Act: -0.1700

Data Index: 4610247 (Open Web Text)

Max Activating Token Index: 934

Text #14

Max Range: 11.3943. Min Range: -11.3943

Max Act: 10.2670. Min Act: -0.1700

Data Index: 5882168 (Open Web Text)

Max Activating Token Index: 71

Text #15

Max Range: 11.3943. Min Range: -11.3943

Max Act: 10.1601. Min Act: -0.1700

Data Index: 3471208 (Open Web Text)

Max Activating Token Index: 568

Text #16

Max Range: 11.3943. Min Range: -11.3943

Max Act: 10.2468. Min Act: -0.1700

Data Index: 4092046 (Open Web Text)

Max Activating Token Index: 429

Text #17

Max Range: 11.3943. Min Range: -11.3943

Max Act: 10.1583. Min Act: -0.1700

Data Index: 5061019 (Open Web Text)

Max Activating Token Index: 612

Text #18

Max Range: 11.3943. Min Range: -11.3943

Max Act: 10.2798. Min Act: -0.1700

Data Index: 5936973 (Open Web Text)

Max Activating Token Index: 370

Text #19

Max Range: 11.3943. Min Range: -11.3943

Max Act: 10.1254. Min Act: -0.1700

Data Index: 6351351 (Open Web Text)

Max Activating Token Index: 122