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

Dataset: Open Web Text

Neuron 505 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: 1.4226. Min Range: -1.4226

Max Act: 1.4226. Min Act: -0.1700

Data Index: 5797259 (Open Web Text)

Max Activating Token Index: 457

Text #1

Max Range: 1.4226. Min Range: -1.4226

Max Act: 1.3423. Min Act: -0.1700

Data Index: 2053702 (Open Web Text)

Max Activating Token Index: 924

Text #2

Max Range: 1.4226. Min Range: -1.4226

Max Act: 1.3554. Min Act: -0.1700

Data Index: 2876431 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 1.4226. Min Range: -1.4226

Max Act: 1.3401. Min Act: -0.1700

Data Index: 5877346 (Open Web Text)

Max Activating Token Index: 52

Text #4

Max Range: 1.4226. Min Range: -1.4226

Max Act: 1.3431. Min Act: -0.1700

Data Index: 593007 (Open Web Text)

Max Activating Token Index: 812

Text #5

Max Range: 1.4226. Min Range: -1.4226

Max Act: 1.3339. Min Act: -0.1700

Data Index: 2156092 (Open Web Text)

Max Activating Token Index: 93

Text #6

Max Range: 1.4226. Min Range: -1.4226

Max Act: 1.3309. Min Act: -0.1700

Data Index: 8744361 (Open Web Text)

Max Activating Token Index: 225

Text #7

Max Range: 1.4226. Min Range: -1.4226

Max Act: 1.3135. Min Act: -0.1700

Data Index: 8450035 (Open Web Text)

Max Activating Token Index: 745

Text #8

Max Range: 1.4226. Min Range: -1.4226

Max Act: 1.3098. Min Act: -0.1700

Data Index: 2511009 (Open Web Text)

Max Activating Token Index: 667

Text #9

Max Range: 1.4226. Min Range: -1.4226

Max Act: 1.2917. Min Act: -0.1699

Data Index: 6994971 (Open Web Text)

Max Activating Token Index: 369

Text #10

Max Range: 1.4226. Min Range: -1.4226

Max Act: 1.3054. Min Act: -0.1698

Data Index: 6675639 (Open Web Text)

Max Activating Token Index: 201

Text #11

Max Range: 1.4226. Min Range: -1.4226

Max Act: 1.3021. Min Act: -0.1700

Data Index: 1380443 (Open Web Text)

Max Activating Token Index: 348

Text #12

Max Range: 1.4226. Min Range: -1.4226

Max Act: 1.2964. Min Act: -0.1700

Data Index: 8330288 (Open Web Text)

Max Activating Token Index: 436

Text #13

Max Range: 1.4226. Min Range: -1.4226

Max Act: 1.3032. Min Act: -0.1700

Data Index: 3540294 (Open Web Text)

Max Activating Token Index: 828

Text #14

Max Range: 1.4226. Min Range: -1.4226

Max Act: 1.3045. Min Act: -0.1700

Data Index: 8700804 (Open Web Text)

Max Activating Token Index: 801

Text #15

Max Range: 1.4226. Min Range: -1.4226

Max Act: 1.2985. Min Act: -0.1700

Data Index: 6030396 (Open Web Text)

Max Activating Token Index: 659

Text #16

Max Range: 1.4226. Min Range: -1.4226

Max Act: 1.2938. Min Act: -0.1700

Data Index: 481939 (Open Web Text)

Max Activating Token Index: 695

Text #17

Max Range: 1.4226. Min Range: -1.4226

Max Act: 1.2837. Min Act: -0.1700

Data Index: 5428481 (Open Web Text)

Max Activating Token Index: 251

Text #18

Max Range: 1.4226. Min Range: -1.4226

Max Act: 1.2821. Min Act: -0.1700

Data Index: 3407341 (Open Web Text)

Max Activating Token Index: 788

Text #19

Max Range: 1.4226. Min Range: -1.4226

Max Act: 1.2865. Min Act: -0.1700

Data Index: 6879318 (Open Web Text)

Max Activating Token Index: 327