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

Dataset: Open Web Text

Neuron 1456 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: 1.0385. Min Range: -1.0385

Max Act: 1.0385. Min Act: -0.0978

Data Index: 8337023 (Open Web Text)

Max Activating Token Index: 304

Text #1

Max Range: 1.0385. Min Range: -1.0385

Max Act: 1.0246. Min Act: -0.1243

Data Index: 126850 (Open Web Text)

Max Activating Token Index: 362

Text #2

Max Range: 1.0385. Min Range: -1.0385

Max Act: 1.0240. Min Act: -0.1106

Data Index: 3188264 (Open Web Text)

Max Activating Token Index: 935

Text #3

Max Range: 1.0385. Min Range: -1.0385

Max Act: 1.0254. Min Act: -0.1161

Data Index: 4090033 (Open Web Text)

Max Activating Token Index: 347

Text #4

Max Range: 1.0385. Min Range: -1.0385

Max Act: 1.0181. Min Act: -0.1198

Data Index: 683301 (Open Web Text)

Max Activating Token Index: 833

Text #5

Max Range: 1.0385. Min Range: -1.0385

Max Act: 1.0226. Min Act: -0.1007

Data Index: 6809165 (Open Web Text)

Max Activating Token Index: 973

Text #6

Max Range: 1.0385. Min Range: -1.0385

Max Act: 1.0144. Min Act: -0.0975

Data Index: 762027 (Open Web Text)

Max Activating Token Index: 598

Text #7

Max Range: 1.0385. Min Range: -1.0385

Max Act: 1.0105. Min Act: -0.1274

Data Index: 6784847 (Open Web Text)

Max Activating Token Index: 636

Text #8

Max Range: 1.0385. Min Range: -1.0385

Max Act: 1.0051. Min Act: -0.0955

Data Index: 6064328 (Open Web Text)

Max Activating Token Index: 632

Text #9

Max Range: 1.0385. Min Range: -1.0385

Max Act: 1.0043. Min Act: -0.1222

Data Index: 8721665 (Open Web Text)

Max Activating Token Index: 690

Text #10

Max Range: 1.0385. Min Range: -1.0385

Max Act: 1.0038. Min Act: -0.1147

Data Index: 8213937 (Open Web Text)

Max Activating Token Index: 998

Text #11

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.9945. Min Act: -0.0926

Data Index: 7577104 (Open Web Text)

Max Activating Token Index: 482

Text #12

Max Range: 1.0385. Min Range: -1.0385

Max Act: 1.0045. Min Act: -0.1145

Data Index: 86550 (Open Web Text)

Max Activating Token Index: 270

Text #13

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.9980. Min Act: -0.1149

Data Index: 915442 (Open Web Text)

Max Activating Token Index: 241

Text #14

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.9995. Min Act: -0.1559

Data Index: 3436619 (Open Web Text)

Max Activating Token Index: 449

Text #15

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.9950. Min Act: -0.1152

Data Index: 479257 (Open Web Text)

Max Activating Token Index: 554

Text #16

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.9960. Min Act: -0.1477

Data Index: 1417416 (Open Web Text)

Max Activating Token Index: 635

Text #17

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.9919. Min Act: -0.1384

Data Index: 5551397 (Open Web Text)

Max Activating Token Index: 184

Text #18

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.9844. Min Act: -0.1244

Data Index: 6803564 (Open Web Text)

Max Activating Token Index: 969

Text #19

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.9824. Min Act: -0.1234

Data Index: 5519217 (Open Web Text)

Max Activating Token Index: 686