Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3646 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4860. Min Range: -5.4860
Max Act: 5.4860. Min Act: -0.1700
Data Index: 55561 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4860. Min Range: -5.4860
Max Act: 5.4235. Min Act: -0.1700
Data Index: 2455503 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4860. Min Range: -5.4860
Max Act: 5.4235. Min Act: -0.1700
Data Index: 7270396 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4860. Min Range: -5.4860
Max Act: 5.3923. Min Act: -0.1700
Data Index: 7526255 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4860. Min Range: -5.4860
Max Act: 5.3923. Min Act: -0.1700
Data Index: 4010455 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4860. Min Range: -5.4860
Max Act: 5.2985. Min Act: -0.1700
Data Index: 5873091 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4860. Min Range: -5.4860
Max Act: 5.2985. Min Act: -0.1700
Data Index: 5771264 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4860. Min Range: -5.4860
Max Act: 5.2985. Min Act: -0.1700
Data Index: 4010457 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4860. Min Range: -5.4860
Max Act: 5.2985. Min Act: -0.1700
Data Index: 8403028 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4860. Min Range: -5.4860
Max Act: 5.2360. Min Act: -0.1700
Data Index: 8575097 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4860. Min Range: -5.4860
Max Act: 5.2048. Min Act: -0.1700
Data Index: 34476 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4860. Min Range: -5.4860
Max Act: 5.2048. Min Act: -0.1700
Data Index: 7222831 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4860. Min Range: -5.4860
Max Act: 5.2048. Min Act: -0.1700
Data Index: 24947 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4860. Min Range: -5.4860
Max Act: 5.2048. Min Act: -0.1700
Data Index: 4326403 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4860. Min Range: -5.4860
Max Act: 5.2048. Min Act: -0.1700
Data Index: 2708824 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4860. Min Range: -5.4860
Max Act: 5.1735. Min Act: -0.1700
Data Index: 82634 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4860. Min Range: -5.4860
Max Act: 5.1735. Min Act: -0.1700
Data Index: 2255035 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4860. Min Range: -5.4860
Max Act: 5.1423. Min Act: -0.1700
Data Index: 4966098 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4860. Min Range: -5.4860
Max Act: 5.2048. Min Act: -0.1700
Data Index: 7169079 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4860. Min Range: -5.4860
Max Act: 5.2048. Min Act: -0.1700
Data Index: 1119273 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19