Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1446 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3500. Min Range: -4.3500
Max Act: 4.3500. Min Act: -0.1700
Data Index: 2288927 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3500. Min Range: -4.3500
Max Act: 4.3187. Min Act: -0.1700
Data Index: 155666 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3500. Min Range: -4.3500
Max Act: 4.2875. Min Act: -0.1700
Data Index: 2977980 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3500. Min Range: -4.3500
Max Act: 4.2875. Min Act: -0.1700
Data Index: 1255714 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3500. Min Range: -4.3500
Max Act: 4.2562. Min Act: -0.1700
Data Index: 3428346 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3500. Min Range: -4.3500
Max Act: 4.2875. Min Act: -0.1700
Data Index: 3573463 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3500. Min Range: -4.3500
Max Act: 4.2250. Min Act: -0.1700
Data Index: 3018920 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3500. Min Range: -4.3500
Max Act: 4.1937. Min Act: -0.1700
Data Index: 5513476 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3500. Min Range: -4.3500
Max Act: 4.1312. Min Act: -0.1700
Data Index: 2796946 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3500. Min Range: -4.3500
Max Act: 4.1625. Min Act: -0.1700
Data Index: 6313 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3500. Min Range: -4.3500
Max Act: 4.1625. Min Act: -0.1700
Data Index: 844665 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3500. Min Range: -4.3500
Max Act: 4.1312. Min Act: -0.1700
Data Index: 4349951 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3500. Min Range: -4.3500
Max Act: 4.1625. Min Act: -0.1700
Data Index: 8137141 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3500. Min Range: -4.3500
Max Act: 4.1312. Min Act: -0.1700
Data Index: 925328 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3500. Min Range: -4.3500
Max Act: 4.1312. Min Act: -0.1700
Data Index: 6490770 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3500. Min Range: -4.3500
Max Act: 4.1625. Min Act: -0.1700
Data Index: 7130422 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3500. Min Range: -4.3500
Max Act: 4.1000. Min Act: -0.1700
Data Index: 779701 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3500. Min Range: -4.3500
Max Act: 4.1000. Min Act: -0.1700
Data Index: 3554597 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3500. Min Range: -4.3500
Max Act: 4.1000. Min Act: -0.1700
Data Index: 5775817 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3500. Min Range: -4.3500
Max Act: 4.1000. Min Act: -0.1700
Data Index: 1942626 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #19