Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1206 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7003. Min Range: -2.7003
Max Act: 2.7003. Min Act: -0.1700
Data Index: 3765485 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7003. Min Range: -2.7003
Max Act: 2.5879. Min Act: -0.1700
Data Index: 6746919 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7003. Min Range: -2.7003
Max Act: 2.6040. Min Act: -0.1700
Data Index: 8604808 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7003. Min Range: -2.7003
Max Act: 2.6040. Min Act: -0.1700
Data Index: 7580936 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7003. Min Range: -2.7003
Max Act: 2.5718. Min Act: -0.1700
Data Index: 4176189 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7003. Min Range: -2.7003
Max Act: 2.5395. Min Act: -0.1700
Data Index: 1685706 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7003. Min Range: -2.7003
Max Act: 2.5557. Min Act: -0.1700
Data Index: 1872754 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7003. Min Range: -2.7003
Max Act: 2.5395. Min Act: -0.1700
Data Index: 1803491 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7003. Min Range: -2.7003
Max Act: 2.4910. Min Act: -0.1700
Data Index: 8627594 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7003. Min Range: -2.7003
Max Act: 2.4910. Min Act: -0.1700
Data Index: 3065423 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7003. Min Range: -2.7003
Max Act: 2.5072. Min Act: -0.1700
Data Index: 7376584 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7003. Min Range: -2.7003
Max Act: 2.4748. Min Act: -0.1700
Data Index: 2512749 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7003. Min Range: -2.7003
Max Act: 2.4585. Min Act: -0.1700
Data Index: 5376433 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7003. Min Range: -2.7003
Max Act: 2.4748. Min Act: -0.1700
Data Index: 4049916 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7003. Min Range: -2.7003
Max Act: 2.4748. Min Act: -0.1700
Data Index: 1551126 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7003. Min Range: -2.7003
Max Act: 2.4748. Min Act: -0.1700
Data Index: 7310792 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7003. Min Range: -2.7003
Max Act: 2.4748. Min Act: -0.1700
Data Index: 2600243 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7003. Min Range: -2.7003
Max Act: 2.4748. Min Act: -0.1700
Data Index: 1336787 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7003. Min Range: -2.7003
Max Act: 2.4585. Min Act: -0.1700
Data Index: 7562018 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7003. Min Range: -2.7003
Max Act: 2.4748. Min Act: -0.1700
Data Index: 2545064 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19