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

Dataset: Open Web Text

Neuron 227 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: 4.5174. Min Range: -4.5174

Max Act: 4.5174. Min Act: -0.1700

Data Index: 2509276 (Open Web Text)

Max Activating Token Index: 254

Text #1

Max Range: 4.5174. Min Range: -4.5174

Max Act: 4.4567. Min Act: -0.1700

Data Index: 6029101 (Open Web Text)

Max Activating Token Index: 538

Text #2

Max Range: 4.5174. Min Range: -4.5174

Max Act: 4.4225. Min Act: -0.1698

Data Index: 5489693 (Open Web Text)

Max Activating Token Index: 99

Text #3

Max Range: 4.5174. Min Range: -4.5174

Max Act: 4.3911. Min Act: -0.1700

Data Index: 4925761 (Open Web Text)

Max Activating Token Index: 367

Text #4

Max Range: 4.5174. Min Range: -4.5174

Max Act: 4.4037. Min Act: -0.1700

Data Index: 8296827 (Open Web Text)

Max Activating Token Index: 146

Text #5

Max Range: 4.5174. Min Range: -4.5174

Max Act: 4.3467. Min Act: -0.1700

Data Index: 304565 (Open Web Text)

Max Activating Token Index: 370

Text #6

Max Range: 4.5174. Min Range: -4.5174

Max Act: 4.3770. Min Act: -0.1700

Data Index: 2205447 (Open Web Text)

Max Activating Token Index: 136

Text #7

Max Range: 4.5174. Min Range: -4.5174

Max Act: 4.3444. Min Act: -0.1700

Data Index: 1335464 (Open Web Text)

Max Activating Token Index: 705

Text #8

Max Range: 4.5174. Min Range: -4.5174

Max Act: 4.3528. Min Act: -0.1700

Data Index: 8639644 (Open Web Text)

Max Activating Token Index: 265

Text #9

Max Range: 4.5174. Min Range: -4.5174

Max Act: 4.3618. Min Act: -0.1700

Data Index: 7984965 (Open Web Text)

Max Activating Token Index: 821

Text #10

Max Range: 4.5174. Min Range: -4.5174

Max Act: 4.3502. Min Act: -0.1700

Data Index: 3185668 (Open Web Text)

Max Activating Token Index: 400

Text #11

Max Range: 4.5174. Min Range: -4.5174

Max Act: 4.3495. Min Act: -0.1700

Data Index: 6759584 (Open Web Text)

Max Activating Token Index: 841

Text #12

Max Range: 4.5174. Min Range: -4.5174

Max Act: 4.3236. Min Act: -0.1700

Data Index: 2488135 (Open Web Text)

Max Activating Token Index: 497

Text #13

Max Range: 4.5174. Min Range: -4.5174

Max Act: 4.3401. Min Act: -0.1700

Data Index: 8829471 (Open Web Text)

Max Activating Token Index: 149

Text #14

Max Range: 4.5174. Min Range: -4.5174

Max Act: 4.3475. Min Act: -0.1700

Data Index: 8309109 (Open Web Text)

Max Activating Token Index: 503

Text #15

Max Range: 4.5174. Min Range: -4.5174

Max Act: 4.3225. Min Act: -0.1700

Data Index: 4815264 (Open Web Text)

Max Activating Token Index: 161

Text #16

Max Range: 4.5174. Min Range: -4.5174

Max Act: 4.3333. Min Act: -0.1700

Data Index: 6728913 (Open Web Text)

Max Activating Token Index: 568

Text #17

Max Range: 4.5174. Min Range: -4.5174

Max Act: 4.3334. Min Act: -0.1700

Data Index: 6367760 (Open Web Text)

Max Activating Token Index: 585

Text #18

Max Range: 4.5174. Min Range: -4.5174

Max Act: 4.3171. Min Act: -0.1700

Data Index: 4862120 (Open Web Text)

Max Activating Token Index: 224

Text #19

Max Range: 4.5174. Min Range: -4.5174

Max Act: 4.3132. Min Act: -0.1700

Data Index: 4683031 (Open Web Text)

Max Activating Token Index: 406