Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 573 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9020. Min Range: -1.9020
Max Act: 1.9020. Min Act: -0.1621
Data Index: 236116 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9020. Min Range: -1.9020
Max Act: 1.8336. Min Act: -0.1692
Data Index: 3725536 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9020. Min Range: -1.9020
Max Act: 1.7820. Min Act: -0.1423
Data Index: 3725534 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9020. Min Range: -1.9020
Max Act: 1.7388. Min Act: -0.1587
Data Index: 236102 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9020. Min Range: -1.9020
Max Act: 1.7388. Min Act: -0.1675
Data Index: 236117 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9020. Min Range: -1.9020
Max Act: 1.7215. Min Act: -0.1697
Data Index: 120503 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9020. Min Range: -1.9020
Max Act: 1.6955. Min Act: -0.1698
Data Index: 5836524 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9020. Min Range: -1.9020
Max Act: 1.6782. Min Act: -0.1700
Data Index: 6396840 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9020. Min Range: -1.9020
Max Act: 1.6782. Min Act: -0.1686
Data Index: 7428190 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9020. Min Range: -1.9020
Max Act: 1.6695. Min Act: -0.1699
Data Index: 1139960 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9020. Min Range: -1.9020
Max Act: 1.6608. Min Act: -0.1700
Data Index: 3055987 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9020. Min Range: -1.9020
Max Act: 1.6695. Min Act: -0.1700
Data Index: 8515311 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9020. Min Range: -1.9020
Max Act: 1.6608. Min Act: -0.1700
Data Index: 786929 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9020. Min Range: -1.9020
Max Act: 1.6608. Min Act: -0.1700
Data Index: 4708854 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9020. Min Range: -1.9020
Max Act: 1.6608. Min Act: -0.1697
Data Index: 3728632 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9020. Min Range: -1.9020
Max Act: 1.6608. Min Act: -0.1700
Data Index: 2205484 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9020. Min Range: -1.9020
Max Act: 1.6608. Min Act: -0.1699
Data Index: 2904926 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9020. Min Range: -1.9020
Max Act: 1.6608. Min Act: -0.1700
Data Index: 3501138 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9020. Min Range: -1.9020
Max Act: 1.6521. Min Act: -0.1545
Data Index: 236115 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9020. Min Range: -1.9020
Max Act: 1.6521. Min Act: -0.1596
Data Index: 5362757 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19