Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4827 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4031. Min Range: -5.4031
Max Act: 5.4031. Min Act: -0.1700
Data Index: 412712 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4031. Min Range: -5.4031
Max Act: 5.1218. Min Act: -0.1700
Data Index: 2089220 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4031. Min Range: -5.4031
Max Act: 5.1531. Min Act: -0.1700
Data Index: 5764448 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4031. Min Range: -5.4031
Max Act: 5.1531. Min Act: -0.1700
Data Index: 4987072 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4031. Min Range: -5.4031
Max Act: 5.1531. Min Act: -0.1700
Data Index: 7727856 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4031. Min Range: -5.4031
Max Act: 5.1218. Min Act: -0.1700
Data Index: 2480218 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4031. Min Range: -5.4031
Max Act: 5.1531. Min Act: -0.1700
Data Index: 3189978 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4031. Min Range: -5.4031
Max Act: 5.0906. Min Act: -0.1700
Data Index: 8399108 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4031. Min Range: -5.4031
Max Act: 5.0906. Min Act: -0.1700
Data Index: 8100515 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4031. Min Range: -5.4031
Max Act: 5.0906. Min Act: -0.1700
Data Index: 950065 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4031. Min Range: -5.4031
Max Act: 5.0906. Min Act: -0.1700
Data Index: 6634682 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4031. Min Range: -5.4031
Max Act: 5.0906. Min Act: -0.1700
Data Index: 6182962 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4031. Min Range: -5.4031
Max Act: 5.0906. Min Act: -0.1700
Data Index: 5778415 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4031. Min Range: -5.4031
Max Act: 5.0906. Min Act: -0.1700
Data Index: 3361353 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4031. Min Range: -5.4031
Max Act: 5.0593. Min Act: -0.1700
Data Index: 3085601 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4031. Min Range: -5.4031
Max Act: 5.0593. Min Act: -0.1700
Data Index: 6681000 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4031. Min Range: -5.4031
Max Act: 5.0593. Min Act: -0.1700
Data Index: 7190301 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4031. Min Range: -5.4031
Max Act: 5.0593. Min Act: -0.1700
Data Index: 1681709 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4031. Min Range: -5.4031
Max Act: 5.0593. Min Act: -0.1700
Data Index: 29801 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4031. Min Range: -5.4031
Max Act: 5.0593. Min Act: -0.1700
Data Index: 134696 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19