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

Dataset: Open Web Text

Neuron 116 in Layer 5

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: 3.9956. Min Range: -3.9956

Max Act: 3.9956. Min Act: -0.1700

Data Index: 2614796 (Open Web Text)

Max Activating Token Index: 877

Text #1

Max Range: 3.9956. Min Range: -3.9956

Max Act: 3.9795. Min Act: -0.1700

Data Index: 8005890 (Open Web Text)

Max Activating Token Index: 887

Text #2

Max Range: 3.9956. Min Range: -3.9956

Max Act: 3.9487. Min Act: -0.1700

Data Index: 85144 (Open Web Text)

Max Activating Token Index: 580

Text #3

Max Range: 3.9956. Min Range: -3.9956

Max Act: 3.9152. Min Act: -0.1700

Data Index: 5946258 (Open Web Text)

Max Activating Token Index: 300

Text #4

Max Range: 3.9956. Min Range: -3.9956

Max Act: 3.8517. Min Act: -0.1700

Data Index: 8804941 (Open Web Text)

Max Activating Token Index: 374

Text #5

Max Range: 3.9956. Min Range: -3.9956

Max Act: 3.8333. Min Act: -0.1700

Data Index: 8618163 (Open Web Text)

Max Activating Token Index: 178

Text #6

Max Range: 3.9956. Min Range: -3.9956

Max Act: 3.8165. Min Act: -0.1700

Data Index: 4148640 (Open Web Text)

Max Activating Token Index: 970

Text #7

Max Range: 3.9956. Min Range: -3.9956

Max Act: 3.8023. Min Act: -0.1700

Data Index: 8544989 (Open Web Text)

Max Activating Token Index: 579

Text #8

Max Range: 3.9956. Min Range: -3.9956

Max Act: 3.8334. Min Act: -0.1700

Data Index: 8086448 (Open Web Text)

Max Activating Token Index: 329

Text #9

Max Range: 3.9956. Min Range: -3.9956

Max Act: 3.8243. Min Act: -0.1700

Data Index: 5981396 (Open Web Text)

Max Activating Token Index: 244

Text #10

Max Range: 3.9956. Min Range: -3.9956

Max Act: 3.7721. Min Act: -0.1700

Data Index: 5815988 (Open Web Text)

Max Activating Token Index: 205

Text #11

Max Range: 3.9956. Min Range: -3.9956

Max Act: 3.7945. Min Act: -0.1700

Data Index: 1961965 (Open Web Text)

Max Activating Token Index: 943

Text #12

Max Range: 3.9956. Min Range: -3.9956

Max Act: 3.7913. Min Act: -0.1700

Data Index: 2095162 (Open Web Text)

Max Activating Token Index: 251

Text #13

Max Range: 3.9956. Min Range: -3.9956

Max Act: 3.8238. Min Act: -0.1700

Data Index: 2933371 (Open Web Text)

Max Activating Token Index: 304

Text #14

Max Range: 3.9956. Min Range: -3.9956

Max Act: 3.8067. Min Act: -0.1700

Data Index: 7853570 (Open Web Text)

Max Activating Token Index: 336

Text #15

Max Range: 3.9956. Min Range: -3.9956

Max Act: 3.7947. Min Act: -0.1700

Data Index: 4065625 (Open Web Text)

Max Activating Token Index: 985

Text #16

Max Range: 3.9956. Min Range: -3.9956

Max Act: 3.8037. Min Act: -0.1700

Data Index: 5890681 (Open Web Text)

Max Activating Token Index: 702

Text #17

Max Range: 3.9956. Min Range: -3.9956

Max Act: 3.8140. Min Act: -0.1700

Data Index: 1193328 (Open Web Text)

Max Activating Token Index: 981

Text #18

Max Range: 3.9956. Min Range: -3.9956

Max Act: 3.7505. Min Act: -0.1700

Data Index: 788359 (Open Web Text)

Max Activating Token Index: 928

Text #19

Max Range: 3.9956. Min Range: -3.9956

Max Act: 3.7466. Min Act: -0.1700

Data Index: 5325080 (Open Web Text)

Max Activating Token Index: 305