Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1044 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3408. Min Range: -5.3408
Max Act: 5.3408. Min Act: -0.1700
Data Index: 5176627 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3408. Min Range: -5.3408
Max Act: 5.2783. Min Act: -0.1700
Data Index: 5508675 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3408. Min Range: -5.3408
Max Act: 5.1220. Min Act: -0.1700
Data Index: 7742974 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3408. Min Range: -5.3408
Max Act: 5.1220. Min Act: -0.1700
Data Index: 3429659 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3408. Min Range: -5.3408
Max Act: 5.1220. Min Act: -0.1700
Data Index: 2787103 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3408. Min Range: -5.3408
Max Act: 5.0595. Min Act: -0.1700
Data Index: 6605257 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3408. Min Range: -5.3408
Max Act: 5.0908. Min Act: -0.1700
Data Index: 1449677 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3408. Min Range: -5.3408
Max Act: 5.0595. Min Act: -0.1700
Data Index: 6605258 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3408. Min Range: -5.3408
Max Act: 5.0283. Min Act: -0.1700
Data Index: 5914886 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3408. Min Range: -5.3408
Max Act: 5.0283. Min Act: -0.1700
Data Index: 384925 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3408. Min Range: -5.3408
Max Act: 4.9970. Min Act: -0.1700
Data Index: 3064301 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3408. Min Range: -5.3408
Max Act: 4.9970. Min Act: -0.1700
Data Index: 5977890 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3408. Min Range: -5.3408
Max Act: 4.9658. Min Act: -0.1700
Data Index: 6109842 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3408. Min Range: -5.3408
Max Act: 4.9345. Min Act: -0.1700
Data Index: 2735401 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3408. Min Range: -5.3408
Max Act: 4.9033. Min Act: -0.1700
Data Index: 4538817 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3408. Min Range: -5.3408
Max Act: 4.9033. Min Act: -0.1700
Data Index: 5977889 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3408. Min Range: -5.3408
Max Act: 4.9033. Min Act: -0.1700
Data Index: 1217033 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3408. Min Range: -5.3408
Max Act: 4.8720. Min Act: -0.1700
Data Index: 6584018 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3408. Min Range: -5.3408
Max Act: 4.8720. Min Act: -0.1700
Data Index: 4334701 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3408. Min Range: -5.3408
Max Act: 4.8720. Min Act: -0.1700
Data Index: 1329701 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19