Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3767 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8601. Min Range: -3.8601
Max Act: 3.8601. Min Act: -0.1700
Data Index: 6363833 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8601. Min Range: -3.8601
Max Act: 3.8289. Min Act: -0.1700
Data Index: 4563334 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8601. Min Range: -3.8601
Max Act: 3.8289. Min Act: -0.1700
Data Index: 7845896 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8601. Min Range: -3.8601
Max Act: 3.7663. Min Act: -0.1700
Data Index: 5005007 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8601. Min Range: -3.8601
Max Act: 3.7976. Min Act: -0.1700
Data Index: 4956624 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8601. Min Range: -3.8601
Max Act: 3.7976. Min Act: -0.1700
Data Index: 5598024 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8601. Min Range: -3.8601
Max Act: 3.7663. Min Act: -0.1700
Data Index: 7611606 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8601. Min Range: -3.8601
Max Act: 3.7663. Min Act: -0.1700
Data Index: 4163976 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8601. Min Range: -3.8601
Max Act: 3.7976. Min Act: -0.1700
Data Index: 2152624 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8601. Min Range: -3.8601
Max Act: 3.7663. Min Act: -0.1700
Data Index: 2714800 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8601. Min Range: -3.8601
Max Act: 3.7350. Min Act: -0.1700
Data Index: 1560961 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8601. Min Range: -3.8601
Max Act: 3.7350. Min Act: -0.1700
Data Index: 5948350 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8601. Min Range: -3.8601
Max Act: 3.7037. Min Act: -0.1700
Data Index: 6851606 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8601. Min Range: -3.8601
Max Act: 3.7350. Min Act: -0.1700
Data Index: 5471173 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8601. Min Range: -3.8601
Max Act: 3.7037. Min Act: -0.1700
Data Index: 8730057 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8601. Min Range: -3.8601
Max Act: 3.7350. Min Act: -0.1700
Data Index: 7964427 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8601. Min Range: -3.8601
Max Act: 3.7350. Min Act: -0.1700
Data Index: 2287781 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8601. Min Range: -3.8601
Max Act: 3.7037. Min Act: -0.1700
Data Index: 828820 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8601. Min Range: -3.8601
Max Act: 3.7350. Min Act: -0.1700
Data Index: 638225 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8601. Min Range: -3.8601
Max Act: 3.6725. Min Act: -0.1700
Data Index: 3170882 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19