Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3307 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5036. Min Range: -2.5036
Max Act: 2.5036. Min Act: -0.1700
Data Index: 268661 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5036. Min Range: -2.5036
Max Act: 2.3407. Min Act: -0.1700
Data Index: 1964426 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5036. Min Range: -2.5036
Max Act: 2.3242. Min Act: -0.1700
Data Index: 8669336 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5036. Min Range: -2.5036
Max Act: 2.2914. Min Act: -0.1700
Data Index: 3760659 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5036. Min Range: -2.5036
Max Act: 2.2419. Min Act: -0.1700
Data Index: 43123 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5036. Min Range: -2.5036
Max Act: 2.2253. Min Act: -0.1700
Data Index: 1599545 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5036. Min Range: -2.5036
Max Act: 2.2087. Min Act: -0.1700
Data Index: 3819265 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5036. Min Range: -2.5036
Max Act: 2.1922. Min Act: -0.1700
Data Index: 7441396 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5036. Min Range: -2.5036
Max Act: 2.1922. Min Act: -0.1700
Data Index: 6299664 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5036. Min Range: -2.5036
Max Act: 2.1922. Min Act: -0.1700
Data Index: 3299572 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5036. Min Range: -2.5036
Max Act: 2.1755. Min Act: -0.1700
Data Index: 1629605 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5036. Min Range: -2.5036
Max Act: 2.1755. Min Act: -0.1700
Data Index: 658785 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5036. Min Range: -2.5036
Max Act: 2.1422. Min Act: -0.1700
Data Index: 2045828 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5036. Min Range: -2.5036
Max Act: 2.1422. Min Act: -0.1700
Data Index: 7956582 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5036. Min Range: -2.5036
Max Act: 2.1088. Min Act: -0.1700
Data Index: 1323175 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5036. Min Range: -2.5036
Max Act: 2.1255. Min Act: -0.1700
Data Index: 4443234 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5036. Min Range: -2.5036
Max Act: 2.1255. Min Act: -0.1700
Data Index: 5737636 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5036. Min Range: -2.5036
Max Act: 2.1088. Min Act: -0.1700
Data Index: 6736006 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5036. Min Range: -2.5036
Max Act: 2.1088. Min Act: -0.1700
Data Index: 2224633 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5036. Min Range: -2.5036
Max Act: 2.0921. Min Act: -0.1700
Data Index: 3886349 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19