Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 950 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7357. Min Range: -5.7357
Max Act: 5.7357. Min Act: -0.1700
Data Index: 607110 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7357. Min Range: -5.7357
Max Act: 5.3919. Min Act: -0.1700
Data Index: 1241211 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7357. Min Range: -5.7357
Max Act: 5.2669. Min Act: -0.1699
Data Index: 6784206 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7357. Min Range: -5.7357
Max Act: 5.2669. Min Act: -0.1700
Data Index: 122613 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7357. Min Range: -5.7357
Max Act: 5.2357. Min Act: -0.1700
Data Index: 2053007 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7357. Min Range: -5.7357
Max Act: 5.2357. Min Act: -0.1700
Data Index: 6335348 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7357. Min Range: -5.7357
Max Act: 5.2357. Min Act: -0.1700
Data Index: 8096966 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7357. Min Range: -5.7357
Max Act: 5.2357. Min Act: -0.1700
Data Index: 6314079 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7357. Min Range: -5.7357
Max Act: 5.2357. Min Act: -0.1700
Data Index: 2475980 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7357. Min Range: -5.7357
Max Act: 5.2357. Min Act: -0.1700
Data Index: 5837808 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7357. Min Range: -5.7357
Max Act: 5.2357. Min Act: -0.1700
Data Index: 95498 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7357. Min Range: -5.7357
Max Act: 5.2357. Min Act: -0.1700
Data Index: 8760128 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7357. Min Range: -5.7357
Max Act: 5.2357. Min Act: -0.1700
Data Index: 6302435 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7357. Min Range: -5.7357
Max Act: 5.2044. Min Act: -0.1700
Data Index: 8351011 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7357. Min Range: -5.7357
Max Act: 5.2044. Min Act: -0.1700
Data Index: 6509550 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7357. Min Range: -5.7357
Max Act: 5.2044. Min Act: -0.1700
Data Index: 6745746 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7357. Min Range: -5.7357
Max Act: 5.2044. Min Act: -0.1699
Data Index: 5220906 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7357. Min Range: -5.7357
Max Act: 5.2044. Min Act: -0.1700
Data Index: 5063242 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7357. Min Range: -5.7357
Max Act: 5.1732. Min Act: -0.1700
Data Index: 2096634 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7357. Min Range: -5.7357
Max Act: 5.2044. Min Act: -0.1697
Data Index: 4212160 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #19