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

Dataset: Open Web Text

Neuron 2517 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: 4.0194. Min Range: -4.0194

Max Act: 4.0194. Min Act: -0.1700

Data Index: 1197940 (Open Web Text)

Max Activating Token Index: 138

Text #1

Max Range: 4.0194. Min Range: -4.0194

Max Act: 3.9662. Min Act: -0.1700

Data Index: 5282116 (Open Web Text)

Max Activating Token Index: 654

Text #2

Max Range: 4.0194. Min Range: -4.0194

Max Act: 3.9739. Min Act: -0.1700

Data Index: 8273384 (Open Web Text)

Max Activating Token Index: 511

Text #3

Max Range: 4.0194. Min Range: -4.0194

Max Act: 3.8942. Min Act: -0.1700

Data Index: 962186 (Open Web Text)

Max Activating Token Index: 384

Text #4

Max Range: 4.0194. Min Range: -4.0194

Max Act: 3.8879. Min Act: -0.1700

Data Index: 4998148 (Open Web Text)

Max Activating Token Index: 756

Text #5

Max Range: 4.0194. Min Range: -4.0194

Max Act: 3.8618. Min Act: -0.1700

Data Index: 1306620 (Open Web Text)

Max Activating Token Index: 317

Text #6

Max Range: 4.0194. Min Range: -4.0194

Max Act: 3.8457. Min Act: -0.1700

Data Index: 6039673 (Open Web Text)

Max Activating Token Index: 701

Text #7

Max Range: 4.0194. Min Range: -4.0194

Max Act: 3.8368. Min Act: -0.1700

Data Index: 6363393 (Open Web Text)

Max Activating Token Index: 272

Text #8

Max Range: 4.0194. Min Range: -4.0194

Max Act: 3.8553. Min Act: -0.1700

Data Index: 6126957 (Open Web Text)

Max Activating Token Index: 361

Text #9

Max Range: 4.0194. Min Range: -4.0194

Max Act: 3.7924. Min Act: -0.1700

Data Index: 4586896 (Open Web Text)

Max Activating Token Index: 657

Text #10

Max Range: 4.0194. Min Range: -4.0194

Max Act: 3.8068. Min Act: -0.1700

Data Index: 8821105 (Open Web Text)

Max Activating Token Index: 446

Text #11

Max Range: 4.0194. Min Range: -4.0194

Max Act: 3.7964. Min Act: -0.1700

Data Index: 4758358 (Open Web Text)

Max Activating Token Index: 57

Text #12

Max Range: 4.0194. Min Range: -4.0194

Max Act: 3.7919. Min Act: -0.1700

Data Index: 5537944 (Open Web Text)

Max Activating Token Index: 782

Text #13

Max Range: 4.0194. Min Range: -4.0194

Max Act: 3.7855. Min Act: -0.1700

Data Index: 3432218 (Open Web Text)

Max Activating Token Index: 685

Text #14

Max Range: 4.0194. Min Range: -4.0194

Max Act: 3.7906. Min Act: -0.1700

Data Index: 8287452 (Open Web Text)

Max Activating Token Index: 373

Text #15

Max Range: 4.0194. Min Range: -4.0194

Max Act: 3.7925. Min Act: -0.1700

Data Index: 3399140 (Open Web Text)

Max Activating Token Index: 732

Text #16

Max Range: 4.0194. Min Range: -4.0194

Max Act: 3.7668. Min Act: -0.1700

Data Index: 2765823 (Open Web Text)

Max Activating Token Index: 958

Text #17

Max Range: 4.0194. Min Range: -4.0194

Max Act: 3.7897. Min Act: -0.1700

Data Index: 2176818 (Open Web Text)

Max Activating Token Index: 271

Text #18

Max Range: 4.0194. Min Range: -4.0194

Max Act: 3.7411. Min Act: -0.1700

Data Index: 1911154 (Open Web Text)

Max Activating Token Index: 405

Text #19

Max Range: 4.0194. Min Range: -4.0194

Max Act: 3.7617. Min Act: -0.1700

Data Index: 2680762 (Open Web Text)

Max Activating Token Index: 99