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

Dataset: Open Web Text

Neuron 1769 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: 1.9105. Min Range: -1.9105

Max Act: 1.9105. Min Act: -0.1700

Data Index: 8654756 (Open Web Text)

Max Activating Token Index: 889

Text #1

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8556. Min Act: -0.1700

Data Index: 8054224 (Open Web Text)

Max Activating Token Index: 63

Text #2

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8368. Min Act: -0.1700

Data Index: 35845 (Open Web Text)

Max Activating Token Index: 89

Text #3

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8294. Min Act: -0.1696

Data Index: 35844 (Open Web Text)

Max Activating Token Index: 257

Text #4

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8151. Min Act: -0.1700

Data Index: 3264779 (Open Web Text)

Max Activating Token Index: 609

Text #5

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8049. Min Act: -0.1700

Data Index: 4765162 (Open Web Text)

Max Activating Token Index: 47

Text #6

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8033. Min Act: -0.1700

Data Index: 4383701 (Open Web Text)

Max Activating Token Index: 705

Text #7

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8173. Min Act: -0.1700

Data Index: 2843713 (Open Web Text)

Max Activating Token Index: 101

Text #8

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.7891. Min Act: -0.1700

Data Index: 1649006 (Open Web Text)

Max Activating Token Index: 746

Text #9

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.7964. Min Act: -0.1700

Data Index: 887 (Open Web Text)

Max Activating Token Index: 150

Text #10

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.7956. Min Act: -0.1700

Data Index: 1055608 (Open Web Text)

Max Activating Token Index: 205

Text #11

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.7909. Min Act: -0.1699

Data Index: 3264781 (Open Web Text)

Max Activating Token Index: 386

Text #12

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.7886. Min Act: -0.1700

Data Index: 2204023 (Open Web Text)

Max Activating Token Index: 189

Text #13

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.7811. Min Act: -0.1700

Data Index: 5573829 (Open Web Text)

Max Activating Token Index: 149

Text #14

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.7846. Min Act: -0.1700

Data Index: 3264783 (Open Web Text)

Max Activating Token Index: 554

Text #15

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.7863. Min Act: -0.1700

Data Index: 8044130 (Open Web Text)

Max Activating Token Index: 224

Text #16

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.7784. Min Act: -0.1698

Data Index: 3301762 (Open Web Text)

Max Activating Token Index: 437

Text #17

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.7898. Min Act: -0.1697

Data Index: 5458938 (Open Web Text)

Max Activating Token Index: 71

Text #18

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.7845. Min Act: -0.1700

Data Index: 3865509 (Open Web Text)

Max Activating Token Index: 129

Text #19

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.7864. Min Act: -0.1700

Data Index: 2220560 (Open Web Text)

Max Activating Token Index: 609