Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2022 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3746. Min Range: -6.3746
Max Act: 6.3746. Min Act: -0.1700
Data Index: 5004367 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3746. Min Range: -6.3746
Max Act: 6.3121. Min Act: -0.1700
Data Index: 3799758 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3746. Min Range: -6.3746
Max Act: 6.2496. Min Act: -0.1700
Data Index: 6404586 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3746. Min Range: -6.3746
Max Act: 6.2496. Min Act: -0.1700
Data Index: 3730296 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3746. Min Range: -6.3746
Max Act: 6.2496. Min Act: -0.1700
Data Index: 5218018 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3746. Min Range: -6.3746
Max Act: 6.2496. Min Act: -0.1700
Data Index: 3522639 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3746. Min Range: -6.3746
Max Act: 6.1871. Min Act: -0.1700
Data Index: 5958696 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3746. Min Range: -6.3746
Max Act: 6.1871. Min Act: -0.1700
Data Index: 4529080 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3746. Min Range: -6.3746
Max Act: 6.1871. Min Act: -0.1700
Data Index: 6384131 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3746. Min Range: -6.3746
Max Act: 6.1871. Min Act: -0.1700
Data Index: 2146757 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3746. Min Range: -6.3746
Max Act: 6.1558. Min Act: -0.1700
Data Index: 7983330 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3746. Min Range: -6.3746
Max Act: 6.1558. Min Act: -0.1700
Data Index: 8681725 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3746. Min Range: -6.3746
Max Act: 6.1558. Min Act: -0.1700
Data Index: 3777353 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3746. Min Range: -6.3746
Max Act: 6.1558. Min Act: -0.1700
Data Index: 4049708 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3746. Min Range: -6.3746
Max Act: 6.1246. Min Act: -0.1700
Data Index: 178567 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3746. Min Range: -6.3746
Max Act: 6.1246. Min Act: -0.1700
Data Index: 4303472 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3746. Min Range: -6.3746
Max Act: 6.0933. Min Act: -0.1700
Data Index: 605615 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3746. Min Range: -6.3746
Max Act: 6.1558. Min Act: -0.1700
Data Index: 3063805 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3746. Min Range: -6.3746
Max Act: 6.1246. Min Act: -0.1700
Data Index: 977006 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3746. Min Range: -6.3746
Max Act: 6.0933. Min Act: -0.1697
Data Index: 4197007 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19