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

Dataset: Open Web Text

Neuron 565 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: 3.4157. Min Range: -3.4157

Max Act: 3.4157. Min Act: -0.1700

Data Index: 5535805 (Open Web Text)

Max Activating Token Index: 79

Text #1

Max Range: 3.4157. Min Range: -3.4157

Max Act: 3.3440. Min Act: -0.1700

Data Index: 4532944 (Open Web Text)

Max Activating Token Index: 520

Text #2

Max Range: 3.4157. Min Range: -3.4157

Max Act: 3.3411. Min Act: -0.1700

Data Index: 4694099 (Open Web Text)

Max Activating Token Index: 450

Text #3

Max Range: 3.4157. Min Range: -3.4157

Max Act: 3.3422. Min Act: -0.1700

Data Index: 7796973 (Open Web Text)

Max Activating Token Index: 888

Text #4

Max Range: 3.4157. Min Range: -3.4157

Max Act: 3.3447. Min Act: -0.1700

Data Index: 8815709 (Open Web Text)

Max Activating Token Index: 105

Text #5

Max Range: 3.4157. Min Range: -3.4157

Max Act: 3.3435. Min Act: -0.1700

Data Index: 3359141 (Open Web Text)

Max Activating Token Index: 371

Text #6

Max Range: 3.4157. Min Range: -3.4157

Max Act: 3.3084. Min Act: -0.1700

Data Index: 8815715 (Open Web Text)

Max Activating Token Index: 244

Text #7

Max Range: 3.4157. Min Range: -3.4157

Max Act: 3.2983. Min Act: -0.1700

Data Index: 2260252 (Open Web Text)

Max Activating Token Index: 465

Text #8

Max Range: 3.4157. Min Range: -3.4157

Max Act: 3.3022. Min Act: -0.1700

Data Index: 860778 (Open Web Text)

Max Activating Token Index: 232

Text #9

Max Range: 3.4157. Min Range: -3.4157

Max Act: 3.3077. Min Act: -0.1700

Data Index: 7206693 (Open Web Text)

Max Activating Token Index: 366

Text #10

Max Range: 3.4157. Min Range: -3.4157

Max Act: 3.2566. Min Act: -0.1700

Data Index: 902288 (Open Web Text)

Max Activating Token Index: 301

Text #11

Max Range: 3.4157. Min Range: -3.4157

Max Act: 3.2779. Min Act: -0.1700

Data Index: 2177208 (Open Web Text)

Max Activating Token Index: 242

Text #12

Max Range: 3.4157. Min Range: -3.4157

Max Act: 3.2613. Min Act: -0.1700

Data Index: 3319294 (Open Web Text)

Max Activating Token Index: 352

Text #13

Max Range: 3.4157. Min Range: -3.4157

Max Act: 3.2519. Min Act: -0.1700

Data Index: 818040 (Open Web Text)

Max Activating Token Index: 140

Text #14

Max Range: 3.4157. Min Range: -3.4157

Max Act: 3.2540. Min Act: -0.1700

Data Index: 3319292 (Open Web Text)

Max Activating Token Index: 331

Text #15

Max Range: 3.4157. Min Range: -3.4157

Max Act: 3.2534. Min Act: -0.1700

Data Index: 7201257 (Open Web Text)

Max Activating Token Index: 786

Text #16

Max Range: 3.4157. Min Range: -3.4157

Max Act: 3.2522. Min Act: -0.1700

Data Index: 1487026 (Open Web Text)

Max Activating Token Index: 957

Text #17

Max Range: 3.4157. Min Range: -3.4157

Max Act: 3.2605. Min Act: -0.1700

Data Index: 8301089 (Open Web Text)

Max Activating Token Index: 292

Text #18

Max Range: 3.4157. Min Range: -3.4157

Max Act: 3.2632. Min Act: -0.1700

Data Index: 1176418 (Open Web Text)

Max Activating Token Index: 137

Text #19

Max Range: 3.4157. Min Range: -3.4157

Max Act: 3.2487. Min Act: -0.1700

Data Index: 208525 (Open Web Text)

Max Activating Token Index: 939