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

Dataset: Open Web Text

Neuron 788 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: 5.4434. Min Range: -5.4434

Max Act: 5.4434. Min Act: -0.1700

Data Index: 3872346 (Open Web Text)

Max Activating Token Index: 284

Text #1

Max Range: 5.4434. Min Range: -5.4434

Max Act: 5.4077. Min Act: -0.1700

Data Index: 8080569 (Open Web Text)

Max Activating Token Index: 176

Text #2

Max Range: 5.4434. Min Range: -5.4434

Max Act: 5.3792. Min Act: -0.1700

Data Index: 8267829 (Open Web Text)

Max Activating Token Index: 52

Text #3

Max Range: 5.4434. Min Range: -5.4434

Max Act: 5.3064. Min Act: -0.1700

Data Index: 2201815 (Open Web Text)

Max Activating Token Index: 288

Text #4

Max Range: 5.4434. Min Range: -5.4434

Max Act: 5.2524. Min Act: -0.1700

Data Index: 7166597 (Open Web Text)

Max Activating Token Index: 324

Text #5

Max Range: 5.4434. Min Range: -5.4434

Max Act: 5.2750. Min Act: -0.1700

Data Index: 2415988 (Open Web Text)

Max Activating Token Index: 892

Text #6

Max Range: 5.4434. Min Range: -5.4434

Max Act: 5.2699. Min Act: -0.1700

Data Index: 6598237 (Open Web Text)

Max Activating Token Index: 68

Text #7

Max Range: 5.4434. Min Range: -5.4434

Max Act: 5.2843. Min Act: -0.1700

Data Index: 8271411 (Open Web Text)

Max Activating Token Index: 136

Text #8

Max Range: 5.4434. Min Range: -5.4434

Max Act: 5.2419. Min Act: -0.1700

Data Index: 8617254 (Open Web Text)

Max Activating Token Index: 211

Text #9

Max Range: 5.4434. Min Range: -5.4434

Max Act: 5.2039. Min Act: -0.1700

Data Index: 7028872 (Open Web Text)

Max Activating Token Index: 747

Text #10

Max Range: 5.4434. Min Range: -5.4434

Max Act: 5.2939. Min Act: -0.1700

Data Index: 309394 (Open Web Text)

Max Activating Token Index: 330

Text #11

Max Range: 5.4434. Min Range: -5.4434

Max Act: 5.2528. Min Act: -0.1700

Data Index: 5279682 (Open Web Text)

Max Activating Token Index: 208

Text #12

Max Range: 5.4434. Min Range: -5.4434

Max Act: 5.2952. Min Act: -0.1700

Data Index: 8543928 (Open Web Text)

Max Activating Token Index: 873

Text #13

Max Range: 5.4434. Min Range: -5.4434

Max Act: 5.2427. Min Act: -0.1700

Data Index: 6055062 (Open Web Text)

Max Activating Token Index: 184

Text #14

Max Range: 5.4434. Min Range: -5.4434

Max Act: 5.2146. Min Act: -0.1700

Data Index: 8292962 (Open Web Text)

Max Activating Token Index: 552

Text #15

Max Range: 5.4434. Min Range: -5.4434

Max Act: 5.2312. Min Act: -0.1700

Data Index: 642148 (Open Web Text)

Max Activating Token Index: 382

Text #16

Max Range: 5.4434. Min Range: -5.4434

Max Act: 5.2371. Min Act: -0.1700

Data Index: 442691 (Open Web Text)

Max Activating Token Index: 188

Text #17

Max Range: 5.4434. Min Range: -5.4434

Max Act: 5.2138. Min Act: -0.1700

Data Index: 1932259 (Open Web Text)

Max Activating Token Index: 986

Text #18

Max Range: 5.4434. Min Range: -5.4434

Max Act: 5.2342. Min Act: -0.1700

Data Index: 2962323 (Open Web Text)

Max Activating Token Index: 340

Text #19

Max Range: 5.4434. Min Range: -5.4434

Max Act: 5.1876. Min Act: -0.1700

Data Index: 8020182 (Open Web Text)

Max Activating Token Index: 850