Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2620 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0187. Min Range: -5.0187
Max Act: 5.0187. Min Act: -0.1700
Data Index: 850102 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.8000. Min Act: -0.1700
Data Index: 2790092 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.7687. Min Act: -0.1700
Data Index: 2651108 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.7375. Min Act: -0.1700
Data Index: 2938025 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.7687. Min Act: -0.1700
Data Index: 8368402 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.7375. Min Act: -0.1700
Data Index: 4354901 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.7375. Min Act: -0.1700
Data Index: 1645153 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.7375. Min Act: -0.1700
Data Index: 4329838 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.7375. Min Act: -0.1700
Data Index: 3765335 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.6750. Min Act: -0.1700
Data Index: 8034331 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.6437. Min Act: -0.1700
Data Index: 7088219 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.6125. Min Act: -0.1700
Data Index: 2527912 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.6125. Min Act: -0.1700
Data Index: 6063811 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.6125. Min Act: -0.1700
Data Index: 2087837 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.5812. Min Act: -0.1700
Data Index: 1667158 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.5812. Min Act: -0.1700
Data Index: 6423857 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.6125. Min Act: -0.1700
Data Index: 6277725 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.5812. Min Act: -0.1700
Data Index: 3506234 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.5812. Min Act: -0.1700
Data Index: 6019325 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.5187. Min Act: -0.1700
Data Index: 3512604 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19