Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3904 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9642. Min Range: -4.9642
Max Act: 4.9642. Min Act: -0.1700
Data Index: 3876795 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9642. Min Range: -4.9642
Max Act: 4.8080. Min Act: -0.1700
Data Index: 8827961 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9642. Min Range: -4.9642
Max Act: 4.7455. Min Act: -0.1700
Data Index: 736960 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9642. Min Range: -4.9642
Max Act: 4.7455. Min Act: -0.1700
Data Index: 3285558 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9642. Min Range: -4.9642
Max Act: 4.6830. Min Act: -0.1700
Data Index: 2118871 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9642. Min Range: -4.9642
Max Act: 4.7142. Min Act: -0.1700
Data Index: 4825055 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9642. Min Range: -4.9642
Max Act: 4.5892. Min Act: -0.1700
Data Index: 6226930 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9642. Min Range: -4.9642
Max Act: 4.5892. Min Act: -0.1700
Data Index: 493995 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9642. Min Range: -4.9642
Max Act: 4.5892. Min Act: -0.1700
Data Index: 8144375 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9642. Min Range: -4.9642
Max Act: 4.5892. Min Act: -0.1700
Data Index: 4329509 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9642. Min Range: -4.9642
Max Act: 4.6205. Min Act: -0.1700
Data Index: 512000 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9642. Min Range: -4.9642
Max Act: 4.6205. Min Act: -0.1700
Data Index: 7117409 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9642. Min Range: -4.9642
Max Act: 4.5580. Min Act: -0.1700
Data Index: 8156943 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9642. Min Range: -4.9642
Max Act: 4.5580. Min Act: -0.1700
Data Index: 7559695 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9642. Min Range: -4.9642
Max Act: 4.5267. Min Act: -0.1700
Data Index: 8036321 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9642. Min Range: -4.9642
Max Act: 4.5267. Min Act: -0.1700
Data Index: 7805711 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9642. Min Range: -4.9642
Max Act: 4.5580. Min Act: -0.1700
Data Index: 7572994 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9642. Min Range: -4.9642
Max Act: 4.5267. Min Act: -0.1700
Data Index: 2901061 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9642. Min Range: -4.9642
Max Act: 4.5267. Min Act: -0.1700
Data Index: 3070071 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9642. Min Range: -4.9642
Max Act: 4.4642. Min Act: -0.1700
Data Index: 4145755 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19