Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3071 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9563. Min Range: -7.9563
Max Act: 7.9563. Min Act: -0.1700
Data Index: 8361067 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9563. Min Range: -7.9563
Max Act: 7.9563. Min Act: -0.1700
Data Index: 7419981 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9563. Min Range: -7.9563
Max Act: 7.9563. Min Act: -0.1700
Data Index: 8677526 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9563. Min Range: -7.9563
Max Act: 7.9563. Min Act: -0.1700
Data Index: 3361825 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9563. Min Range: -7.9563
Max Act: 7.7688. Min Act: -0.1700
Data Index: 296311 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9563. Min Range: -7.9563
Max Act: 7.7063. Min Act: -0.1700
Data Index: 3536237 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9563. Min Range: -7.9563
Max Act: 7.6438. Min Act: -0.1700
Data Index: 7378144 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9563. Min Range: -7.9563
Max Act: 7.5813. Min Act: -0.1700
Data Index: 2435059 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9563. Min Range: -7.9563
Max Act: 7.5813. Min Act: -0.1700
Data Index: 1121201 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9563. Min Range: -7.9563
Max Act: 7.4563. Min Act: -0.1700
Data Index: 2016246 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9563. Min Range: -7.9563
Max Act: 7.4563. Min Act: -0.1700
Data Index: 4221845 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9563. Min Range: -7.9563
Max Act: 7.4563. Min Act: -0.1700
Data Index: 8607777 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9563. Min Range: -7.9563
Max Act: 7.4563. Min Act: -0.1700
Data Index: 5346476 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9563. Min Range: -7.9563
Max Act: 7.4250. Min Act: -0.1700
Data Index: 4924515 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9563. Min Range: -7.9563
Max Act: 7.4250. Min Act: -0.1700
Data Index: 8383320 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9563. Min Range: -7.9563
Max Act: 7.3938. Min Act: -0.1700
Data Index: 7908884 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9563. Min Range: -7.9563
Max Act: 7.4250. Min Act: -0.1700
Data Index: 4113707 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9563. Min Range: -7.9563
Max Act: 7.3938. Min Act: -0.1700
Data Index: 719235 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9563. Min Range: -7.9563
Max Act: 7.3938. Min Act: -0.1700
Data Index: 4377768 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9563. Min Range: -7.9563
Max Act: 7.3938. Min Act: -0.1700
Data Index: 8480114 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19