Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2550 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7914. Min Range: -3.7914
Max Act: 3.7914. Min Act: -0.1700
Data Index: 3631990 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7914. Min Range: -3.7914
Max Act: 3.7601. Min Act: -0.1700
Data Index: 832106 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7914. Min Range: -3.7914
Max Act: 3.6976. Min Act: -0.1700
Data Index: 7948956 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7914. Min Range: -3.7914
Max Act: 3.6976. Min Act: -0.1700
Data Index: 4146569 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7914. Min Range: -3.7914
Max Act: 3.6663. Min Act: -0.1700
Data Index: 8159649 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7914. Min Range: -3.7914
Max Act: 3.6663. Min Act: -0.1700
Data Index: 7789314 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7914. Min Range: -3.7914
Max Act: 3.6663. Min Act: -0.1700
Data Index: 4420965 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7914. Min Range: -3.7914
Max Act: 3.6350. Min Act: -0.1700
Data Index: 7050888 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7914. Min Range: -3.7914
Max Act: 3.6037. Min Act: -0.1700
Data Index: 3374350 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7914. Min Range: -3.7914
Max Act: 3.5724. Min Act: -0.1700
Data Index: 6066668 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7914. Min Range: -3.7914
Max Act: 3.6037. Min Act: -0.1700
Data Index: 2567722 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7914. Min Range: -3.7914
Max Act: 3.6037. Min Act: -0.1700
Data Index: 3431614 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7914. Min Range: -3.7914
Max Act: 3.5724. Min Act: -0.1700
Data Index: 8270068 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7914. Min Range: -3.7914
Max Act: 3.6037. Min Act: -0.1700
Data Index: 793038 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7914. Min Range: -3.7914
Max Act: 3.5724. Min Act: -0.1700
Data Index: 5928725 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7914. Min Range: -3.7914
Max Act: 3.5724. Min Act: -0.1700
Data Index: 6879263 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7914. Min Range: -3.7914
Max Act: 3.5724. Min Act: -0.1700
Data Index: 856346 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7914. Min Range: -3.7914
Max Act: 3.5724. Min Act: -0.1700
Data Index: 3427497 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7914. Min Range: -3.7914
Max Act: 3.5724. Min Act: -0.1700
Data Index: 5585411 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7914. Min Range: -3.7914
Max Act: 3.5411. Min Act: -0.1700
Data Index: 5553571 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19