Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5506 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5463. Min Range: -7.5463
Max Act: 7.5463. Min Act: -0.1700
Data Index: 4988534 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5463. Min Range: -7.5463
Max Act: 7.2650. Min Act: -0.1700
Data Index: 4562 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5463. Min Range: -7.5463
Max Act: 7.0463. Min Act: -0.1700
Data Index: 2800776 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5463. Min Range: -7.5463
Max Act: 6.9838. Min Act: -0.1700
Data Index: 1586004 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5463. Min Range: -7.5463
Max Act: 6.9213. Min Act: -0.1700
Data Index: 8297336 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5463. Min Range: -7.5463
Max Act: 6.8588. Min Act: -0.1700
Data Index: 5196959 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5463. Min Range: -7.5463
Max Act: 6.8275. Min Act: -0.1700
Data Index: 6433415 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5463. Min Range: -7.5463
Max Act: 6.7963. Min Act: -0.1700
Data Index: 347639 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5463. Min Range: -7.5463
Max Act: 6.7963. Min Act: -0.1700
Data Index: 3714113 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5463. Min Range: -7.5463
Max Act: 6.7650. Min Act: -0.1700
Data Index: 7183076 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5463. Min Range: -7.5463
Max Act: 6.7338. Min Act: -0.1700
Data Index: 3118106 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5463. Min Range: -7.5463
Max Act: 6.7025. Min Act: -0.1700
Data Index: 5235558 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5463. Min Range: -7.5463
Max Act: 6.6400. Min Act: -0.1700
Data Index: 478620 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5463. Min Range: -7.5463
Max Act: 6.6400. Min Act: -0.1700
Data Index: 891556 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5463. Min Range: -7.5463
Max Act: 6.6713. Min Act: -0.1700
Data Index: 8003735 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5463. Min Range: -7.5463
Max Act: 6.7025. Min Act: -0.1700
Data Index: 4506870 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5463. Min Range: -7.5463
Max Act: 6.6400. Min Act: -0.1700
Data Index: 234675 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5463. Min Range: -7.5463
Max Act: 6.6088. Min Act: -0.1700
Data Index: 3499694 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5463. Min Range: -7.5463
Max Act: 6.6400. Min Act: -0.1700
Data Index: 744671 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5463. Min Range: -7.5463
Max Act: 6.6088. Min Act: -0.1700
Data Index: 6902906 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19