Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1686 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8923. Min Range: -2.8923
Max Act: 2.8923. Min Act: -0.1700
Data Index: 2000882 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8923. Min Range: -2.8923
Max Act: 2.8764. Min Act: -0.1700
Data Index: 5011031 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8923. Min Range: -2.8923
Max Act: 2.8447. Min Act: -0.1700
Data Index: 1461612 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8923. Min Range: -2.8923
Max Act: 2.7970. Min Act: -0.1700
Data Index: 3282259 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8923. Min Range: -2.8923
Max Act: 2.7810. Min Act: -0.1700
Data Index: 6654435 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8923. Min Range: -2.8923
Max Act: 2.7810. Min Act: -0.1700
Data Index: 555023 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8923. Min Range: -2.8923
Max Act: 2.7491. Min Act: -0.1700
Data Index: 1568733 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8923. Min Range: -2.8923
Max Act: 2.7332. Min Act: -0.1700
Data Index: 1031176 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8923. Min Range: -2.8923
Max Act: 2.7172. Min Act: -0.1700
Data Index: 4307432 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8923. Min Range: -2.8923
Max Act: 2.7172. Min Act: -0.1700
Data Index: 4759109 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8923. Min Range: -2.8923
Max Act: 2.7172. Min Act: -0.1700
Data Index: 1299423 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8923. Min Range: -2.8923
Max Act: 2.7172. Min Act: -0.1700
Data Index: 4874602 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8923. Min Range: -2.8923
Max Act: 2.7332. Min Act: -0.1700
Data Index: 4679728 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8923. Min Range: -2.8923
Max Act: 2.7172. Min Act: -0.1700
Data Index: 1392186 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8923. Min Range: -2.8923
Max Act: 2.7012. Min Act: -0.1700
Data Index: 1385300 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8923. Min Range: -2.8923
Max Act: 2.7332. Min Act: -0.1700
Data Index: 7732223 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8923. Min Range: -2.8923
Max Act: 2.7012. Min Act: -0.1700
Data Index: 1310289 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8923. Min Range: -2.8923
Max Act: 2.7012. Min Act: -0.1700
Data Index: 199463 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8923. Min Range: -2.8923
Max Act: 2.6852. Min Act: -0.1700
Data Index: 948451 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8923. Min Range: -2.8923
Max Act: 2.6852. Min Act: -0.1700
Data Index: 2539290 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19