Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1983 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3045. Min Range: -6.3045
Max Act: 6.3045. Min Act: -0.1700
Data Index: 6056366 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3045. Min Range: -6.3045
Max Act: 6.1795. Min Act: -0.1700
Data Index: 5027862 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3045. Min Range: -6.3045
Max Act: 6.1170. Min Act: -0.1700
Data Index: 8089137 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3045. Min Range: -6.3045
Max Act: 6.0232. Min Act: -0.1700
Data Index: 3813663 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3045. Min Range: -6.3045
Max Act: 6.0232. Min Act: -0.1700
Data Index: 5038659 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3045. Min Range: -6.3045
Max Act: 5.9607. Min Act: -0.1700
Data Index: 4152836 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3045. Min Range: -6.3045
Max Act: 5.8670. Min Act: -0.1700
Data Index: 4223625 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3045. Min Range: -6.3045
Max Act: 5.8045. Min Act: -0.1700
Data Index: 2431826 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3045. Min Range: -6.3045
Max Act: 5.7732. Min Act: -0.1700
Data Index: 4457146 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3045. Min Range: -6.3045
Max Act: 5.6795. Min Act: -0.1700
Data Index: 8619023 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3045. Min Range: -6.3045
Max Act: 5.7107. Min Act: -0.1700
Data Index: 3403625 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3045. Min Range: -6.3045
Max Act: 5.7107. Min Act: -0.1700
Data Index: 8123523 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3045. Min Range: -6.3045
Max Act: 5.7420. Min Act: -0.1700
Data Index: 8601072 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3045. Min Range: -6.3045
Max Act: 5.6795. Min Act: -0.1700
Data Index: 7134011 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3045. Min Range: -6.3045
Max Act: 5.6795. Min Act: -0.1700
Data Index: 2809833 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3045. Min Range: -6.3045
Max Act: 5.6482. Min Act: -0.1700
Data Index: 6113963 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3045. Min Range: -6.3045
Max Act: 5.6170. Min Act: -0.1700
Data Index: 6395248 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3045. Min Range: -6.3045
Max Act: 5.5857. Min Act: -0.1700
Data Index: 6870565 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3045. Min Range: -6.3045
Max Act: 5.6170. Min Act: -0.1700
Data Index: 8722286 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3045. Min Range: -6.3045
Max Act: 5.5857. Min Act: -0.1700
Data Index: 4721292 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19