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

Dataset: Open Web Text

Neuron 245 in Layer 4

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: 4.6142. Min Range: -4.6142

Max Act: 4.6142. Min Act: -0.1700

Data Index: 5882215 (Open Web Text)

Max Activating Token Index: 898

Text #1

Max Range: 4.6142. Min Range: -4.6142

Max Act: 4.4240. Min Act: -0.1700

Data Index: 4808676 (Open Web Text)

Max Activating Token Index: 393

Text #2

Max Range: 4.6142. Min Range: -4.6142

Max Act: 4.3731. Min Act: -0.1700

Data Index: 6918501 (Open Web Text)

Max Activating Token Index: 478

Text #3

Max Range: 4.6142. Min Range: -4.6142

Max Act: 4.3851. Min Act: -0.1700

Data Index: 4592523 (Open Web Text)

Max Activating Token Index: 721

Text #4

Max Range: 4.6142. Min Range: -4.6142

Max Act: 4.3877. Min Act: -0.1700

Data Index: 2745569 (Open Web Text)

Max Activating Token Index: 480

Text #5

Max Range: 4.6142. Min Range: -4.6142

Max Act: 4.3557. Min Act: -0.1700

Data Index: 4205934 (Open Web Text)

Max Activating Token Index: 545

Text #6

Max Range: 4.6142. Min Range: -4.6142

Max Act: 4.3181. Min Act: -0.1700

Data Index: 1051154 (Open Web Text)

Max Activating Token Index: 338

Text #7

Max Range: 4.6142. Min Range: -4.6142

Max Act: 4.3552. Min Act: -0.1700

Data Index: 6158882 (Open Web Text)

Max Activating Token Index: 358

Text #8

Max Range: 4.6142. Min Range: -4.6142

Max Act: 4.3671. Min Act: -0.1700

Data Index: 758537 (Open Web Text)

Max Activating Token Index: 177

Text #9

Max Range: 4.6142. Min Range: -4.6142

Max Act: 4.3443. Min Act: -0.1700

Data Index: 5079945 (Open Web Text)

Max Activating Token Index: 903

Text #10

Max Range: 4.6142. Min Range: -4.6142

Max Act: 4.3839. Min Act: -0.1700

Data Index: 3814179 (Open Web Text)

Max Activating Token Index: 248

Text #11

Max Range: 4.6142. Min Range: -4.6142

Max Act: 4.3002. Min Act: -0.1700

Data Index: 489280 (Open Web Text)

Max Activating Token Index: 312

Text #12

Max Range: 4.6142. Min Range: -4.6142

Max Act: 4.3252. Min Act: -0.1700

Data Index: 8702654 (Open Web Text)

Max Activating Token Index: 895

Text #13

Max Range: 4.6142. Min Range: -4.6142

Max Act: 4.3342. Min Act: -0.1700

Data Index: 1175350 (Open Web Text)

Max Activating Token Index: 834

Text #14

Max Range: 4.6142. Min Range: -4.6142

Max Act: 4.2715. Min Act: -0.1700

Data Index: 8048091 (Open Web Text)

Max Activating Token Index: 741

Text #15

Max Range: 4.6142. Min Range: -4.6142

Max Act: 4.2873. Min Act: -0.1700

Data Index: 8002185 (Open Web Text)

Max Activating Token Index: 382

Text #16

Max Range: 4.6142. Min Range: -4.6142

Max Act: 4.2925. Min Act: -0.1700

Data Index: 2953266 (Open Web Text)

Max Activating Token Index: 718

Text #17

Max Range: 4.6142. Min Range: -4.6142

Max Act: 4.2846. Min Act: -0.1700

Data Index: 3055827 (Open Web Text)

Max Activating Token Index: 913

Text #18

Max Range: 4.6142. Min Range: -4.6142

Max Act: 4.3035. Min Act: -0.1700

Data Index: 6295354 (Open Web Text)

Max Activating Token Index: 581

Text #19

Max Range: 4.6142. Min Range: -4.6142

Max Act: 4.2607. Min Act: -0.1700

Data Index: 3445753 (Open Web Text)

Max Activating Token Index: 350