Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4322 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3764. Min Range: -5.3764
Max Act: 5.3764. Min Act: -0.1700
Data Index: 6343311 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3764. Min Range: -5.3764
Max Act: 5.2514. Min Act: -0.1700
Data Index: 564200 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3764. Min Range: -5.3764
Max Act: 5.2514. Min Act: -0.1700
Data Index: 8104876 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3764. Min Range: -5.3764
Max Act: 5.1889. Min Act: -0.1700
Data Index: 763243 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3764. Min Range: -5.3764
Max Act: 5.1576. Min Act: -0.1700
Data Index: 8648428 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3764. Min Range: -5.3764
Max Act: 5.1264. Min Act: -0.1700
Data Index: 6731039 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3764. Min Range: -5.3764
Max Act: 5.1264. Min Act: -0.1700
Data Index: 5933043 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3764. Min Range: -5.3764
Max Act: 5.1264. Min Act: -0.1700
Data Index: 7253394 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3764. Min Range: -5.3764
Max Act: 5.1264. Min Act: -0.1700
Data Index: 4523769 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3764. Min Range: -5.3764
Max Act: 5.0326. Min Act: -0.1700
Data Index: 7927837 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3764. Min Range: -5.3764
Max Act: 5.0014. Min Act: -0.1700
Data Index: 2493971 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3764. Min Range: -5.3764
Max Act: 5.0326. Min Act: -0.1700
Data Index: 1784982 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3764. Min Range: -5.3764
Max Act: 5.0326. Min Act: -0.1700
Data Index: 645535 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3764. Min Range: -5.3764
Max Act: 5.0014. Min Act: -0.1700
Data Index: 6886824 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3764. Min Range: -5.3764
Max Act: 4.9701. Min Act: -0.1700
Data Index: 8781564 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3764. Min Range: -5.3764
Max Act: 5.0326. Min Act: -0.1700
Data Index: 2256081 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3764. Min Range: -5.3764
Max Act: 5.0014. Min Act: -0.1700
Data Index: 774129 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3764. Min Range: -5.3764
Max Act: 4.9701. Min Act: -0.1700
Data Index: 7891933 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3764. Min Range: -5.3764
Max Act: 4.9701. Min Act: -0.1700
Data Index: 6202455 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3764. Min Range: -5.3764
Max Act: 4.9701. Min Act: -0.1700
Data Index: 2872300 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19