Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4049 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2550. Min Range: -2.2550
Max Act: 2.2550. Min Act: -0.1700
Data Index: 1277689 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2550. Min Range: -2.2550
Max Act: 2.2053. Min Act: -0.1700
Data Index: 4432806 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2550. Min Range: -2.2550
Max Act: 2.1721. Min Act: -0.1700
Data Index: 7813569 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2550. Min Range: -2.2550
Max Act: 2.1721. Min Act: -0.1700
Data Index: 1886847 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2550. Min Range: -2.2550
Max Act: 2.1388. Min Act: -0.1700
Data Index: 5399360 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2550. Min Range: -2.2550
Max Act: 2.1137. Min Act: -0.1700
Data Index: 3512933 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2550. Min Range: -2.2550
Max Act: 2.1137. Min Act: -0.1700
Data Index: 3512900 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2550. Min Range: -2.2550
Max Act: 2.1137. Min Act: -0.1700
Data Index: 3512832 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2550. Min Range: -2.2550
Max Act: 2.1388. Min Act: -0.1700
Data Index: 4343353 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2550. Min Range: -2.2550
Max Act: 2.1137. Min Act: -0.1700
Data Index: 3512868 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2550. Min Range: -2.2550
Max Act: 2.1137. Min Act: -0.1700
Data Index: 3512834 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2550. Min Range: -2.2550
Max Act: 2.1137. Min Act: -0.1700
Data Index: 3512901 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2550. Min Range: -2.2550
Max Act: 2.1137. Min Act: -0.1700
Data Index: 3512833 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2550. Min Range: -2.2550
Max Act: 2.1137. Min Act: -0.1700
Data Index: 3512869 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2550. Min Range: -2.2550
Max Act: 2.1137. Min Act: -0.1700
Data Index: 3512932 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2550. Min Range: -2.2550
Max Act: 2.1137. Min Act: -0.1700
Data Index: 3512816 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2550. Min Range: -2.2550
Max Act: 2.1137. Min Act: -0.1700
Data Index: 3512837 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2550. Min Range: -2.2550
Max Act: 2.1137. Min Act: -0.1700
Data Index: 3512817 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2550. Min Range: -2.2550
Max Act: 2.1137. Min Act: -0.1700
Data Index: 3512835 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2550. Min Range: -2.2550
Max Act: 2.1137. Min Act: -0.1700
Data Index: 3512836 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19