Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2447 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6976. Min Range: -8.6976
Max Act: 8.6976. Min Act: -0.1700
Data Index: 6444120 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6976. Min Range: -8.6976
Max Act: 8.5726. Min Act: -0.1700
Data Index: 8315882 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6976. Min Range: -8.6976
Max Act: 8.5726. Min Act: -0.1700
Data Index: 5511540 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6976. Min Range: -8.6976
Max Act: 8.3851. Min Act: -0.1700
Data Index: 3491040 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6976. Min Range: -8.6976
Max Act: 8.3226. Min Act: -0.1700
Data Index: 3878880 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6976. Min Range: -8.6976
Max Act: 8.2601. Min Act: -0.1700
Data Index: 2679270 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6976. Min Range: -8.6976
Max Act: 8.2601. Min Act: -0.1700
Data Index: 7161863 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6976. Min Range: -8.6976
Max Act: 8.1976. Min Act: -0.1700
Data Index: 4459437 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6976. Min Range: -8.6976
Max Act: 8.1976. Min Act: -0.1700
Data Index: 3180741 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6976. Min Range: -8.6976
Max Act: 8.2601. Min Act: -0.1700
Data Index: 3993352 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6976. Min Range: -8.6976
Max Act: 8.1976. Min Act: -0.1700
Data Index: 4484504 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6976. Min Range: -8.6976
Max Act: 8.1976. Min Act: -0.1700
Data Index: 670599 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6976. Min Range: -8.6976
Max Act: 8.1351. Min Act: -0.1700
Data Index: 7151877 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6976. Min Range: -8.6976
Max Act: 8.1351. Min Act: -0.1700
Data Index: 6270080 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6976. Min Range: -8.6976
Max Act: 8.1351. Min Act: -0.1700
Data Index: 8613873 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6976. Min Range: -8.6976
Max Act: 8.0726. Min Act: -0.1700
Data Index: 4837751 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6976. Min Range: -8.6976
Max Act: 8.1351. Min Act: -0.1700
Data Index: 1280606 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6976. Min Range: -8.6976
Max Act: 8.1351. Min Act: -0.1700
Data Index: 4750537 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6976. Min Range: -8.6976
Max Act: 8.1351. Min Act: -0.1700
Data Index: 7151878 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6976. Min Range: -8.6976
Max Act: 8.0726. Min Act: -0.1700
Data Index: 1544992 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #19