Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2623 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7817. Min Range: -3.7817
Max Act: 3.7817. Min Act: -0.1700
Data Index: 4066290 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7817. Min Range: -3.7817
Max Act: 3.7035. Min Act: -0.1700
Data Index: 3277493 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7817. Min Range: -3.7817
Max Act: 3.7505. Min Act: -0.1700
Data Index: 4234650 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7817. Min Range: -3.7817
Max Act: 3.6879. Min Act: -0.1700
Data Index: 1749696 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7817. Min Range: -3.7817
Max Act: 3.6879. Min Act: -0.1700
Data Index: 7756420 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7817. Min Range: -3.7817
Max Act: 3.7035. Min Act: -0.1700
Data Index: 4117028 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7817. Min Range: -3.7817
Max Act: 3.6253. Min Act: -0.1700
Data Index: 975324 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7817. Min Range: -3.7817
Max Act: 3.5940. Min Act: -0.1700
Data Index: 1111026 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7817. Min Range: -3.7817
Max Act: 3.5784. Min Act: -0.1700
Data Index: 7790125 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7817. Min Range: -3.7817
Max Act: 3.5940. Min Act: -0.1700
Data Index: 1699142 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7817. Min Range: -3.7817
Max Act: 3.5314. Min Act: -0.1700
Data Index: 3016743 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7817. Min Range: -3.7817
Max Act: 3.5157. Min Act: -0.1700
Data Index: 5555464 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7817. Min Range: -3.7817
Max Act: 3.5470. Min Act: -0.1700
Data Index: 7900909 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7817. Min Range: -3.7817
Max Act: 3.5157. Min Act: -0.1700
Data Index: 6398612 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7817. Min Range: -3.7817
Max Act: 3.5314. Min Act: -0.1700
Data Index: 809866 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7817. Min Range: -3.7817
Max Act: 3.4374. Min Act: -0.1700
Data Index: 5119098 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7817. Min Range: -3.7817
Max Act: 3.4687. Min Act: -0.1700
Data Index: 4816483 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7817. Min Range: -3.7817
Max Act: 3.4531. Min Act: -0.1700
Data Index: 4579546 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7817. Min Range: -3.7817
Max Act: 3.4531. Min Act: -0.1700
Data Index: 6235912 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7817. Min Range: -3.7817
Max Act: 3.4531. Min Act: -0.1700
Data Index: 3881773 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19