Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1125 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.8619. Min Range: -8.8619
Max Act: 8.8619. Min Act: -0.1700
Data Index: 6639639 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8619. Min Range: -8.8619
Max Act: 8.6744. Min Act: -0.1700
Data Index: 1501535 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8619. Min Range: -8.8619
Max Act: 8.4244. Min Act: -0.1700
Data Index: 6980372 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8619. Min Range: -8.8619
Max Act: 8.4244. Min Act: -0.1700
Data Index: 5846193 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8619. Min Range: -8.8619
Max Act: 8.2994. Min Act: -0.1700
Data Index: 327374 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8619. Min Range: -8.8619
Max Act: 8.3619. Min Act: -0.1700
Data Index: 4243088 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8619. Min Range: -8.8619
Max Act: 8.3619. Min Act: -0.1700
Data Index: 8159137 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8619. Min Range: -8.8619
Max Act: 8.2994. Min Act: -0.1700
Data Index: 1831363 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8619. Min Range: -8.8619
Max Act: 8.2994. Min Act: -0.1700
Data Index: 3605208 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8619. Min Range: -8.8619
Max Act: 8.2369. Min Act: -0.1700
Data Index: 446057 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8619. Min Range: -8.8619
Max Act: 8.2369. Min Act: -0.1700
Data Index: 261825 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8619. Min Range: -8.8619
Max Act: 8.2369. Min Act: -0.1700
Data Index: 3282603 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8619. Min Range: -8.8619
Max Act: 8.2369. Min Act: -0.1700
Data Index: 2737306 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8619. Min Range: -8.8619
Max Act: 8.2369. Min Act: -0.1700
Data Index: 79705 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8619. Min Range: -8.8619
Max Act: 8.2369. Min Act: -0.1700
Data Index: 797632 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8619. Min Range: -8.8619
Max Act: 8.2369. Min Act: -0.1700
Data Index: 6934501 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8619. Min Range: -8.8619
Max Act: 8.2369. Min Act: -0.1700
Data Index: 5853883 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8619. Min Range: -8.8619
Max Act: 8.1744. Min Act: -0.1700
Data Index: 1980590 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8619. Min Range: -8.8619
Max Act: 8.1744. Min Act: -0.1698
Data Index: 3288049 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8619. Min Range: -8.8619
Max Act: 8.1744. Min Act: -0.1700
Data Index: 503038 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #19