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

Dataset: Open Web Text

Neuron 1355 in Layer 2

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: 1.7935. Min Range: -1.7935

Max Act: 1.7935. Min Act: -0.1700

Data Index: 4079439 (Open Web Text)

Max Activating Token Index: 697

Text #1

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.7807. Min Act: -0.1700

Data Index: 6493463 (Open Web Text)

Max Activating Token Index: 540

Text #2

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.7821. Min Act: -0.1700

Data Index: 6117249 (Open Web Text)

Max Activating Token Index: 430

Text #3

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.7643. Min Act: -0.1700

Data Index: 3642284 (Open Web Text)

Max Activating Token Index: 367

Text #4

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.7676. Min Act: -0.1700

Data Index: 6907776 (Open Web Text)

Max Activating Token Index: 966

Text #5

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.7556. Min Act: -0.1700

Data Index: 6946482 (Open Web Text)

Max Activating Token Index: 712

Text #6

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.7497. Min Act: -0.1700

Data Index: 1149287 (Open Web Text)

Max Activating Token Index: 440

Text #7

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.7482. Min Act: -0.1700

Data Index: 8514312 (Open Web Text)

Max Activating Token Index: 523

Text #8

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.7329. Min Act: -0.1700

Data Index: 5540626 (Open Web Text)

Max Activating Token Index: 140

Text #9

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.7266. Min Act: -0.1700

Data Index: 1143998 (Open Web Text)

Max Activating Token Index: 216

Text #10

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.7175. Min Act: -0.1700

Data Index: 53969 (Open Web Text)

Max Activating Token Index: 443

Text #11

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.7341. Min Act: -0.1700

Data Index: 3200492 (Open Web Text)

Max Activating Token Index: 766

Text #12

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.7348. Min Act: -0.1700

Data Index: 951347 (Open Web Text)

Max Activating Token Index: 353

Text #13

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.7198. Min Act: -0.1700

Data Index: 916950 (Open Web Text)

Max Activating Token Index: 457

Text #14

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.7132. Min Act: -0.1700

Data Index: 5438972 (Open Web Text)

Max Activating Token Index: 1007

Text #15

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.7038. Min Act: -0.1700

Data Index: 119487 (Open Web Text)

Max Activating Token Index: 898

Text #16

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.6909. Min Act: -0.1700

Data Index: 7593640 (Open Web Text)

Max Activating Token Index: 924

Text #17

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.7092. Min Act: -0.1700

Data Index: 3305624 (Open Web Text)

Max Activating Token Index: 429

Text #18

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.7045. Min Act: -0.1700

Data Index: 4581622 (Open Web Text)

Max Activating Token Index: 439

Text #19

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.6956. Min Act: -0.1700

Data Index: 5601293 (Open Web Text)

Max Activating Token Index: 432