Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5548 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5247. Min Range: -5.5247
Max Act: 5.5247. Min Act: -0.1700
Data Index: 7263019 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5247. Min Range: -5.5247
Max Act: 5.3997. Min Act: -0.1700
Data Index: 2895670 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5247. Min Range: -5.5247
Max Act: 5.3684. Min Act: -0.1700
Data Index: 6447246 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5247. Min Range: -5.5247
Max Act: 5.2747. Min Act: -0.1700
Data Index: 2739515 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5247. Min Range: -5.5247
Max Act: 5.2434. Min Act: -0.1700
Data Index: 119963 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5247. Min Range: -5.5247
Max Act: 5.1809. Min Act: -0.1700
Data Index: 8638413 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5247. Min Range: -5.5247
Max Act: 5.1809. Min Act: -0.1700
Data Index: 2865462 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5247. Min Range: -5.5247
Max Act: 5.0559. Min Act: -0.1700
Data Index: 4398558 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5247. Min Range: -5.5247
Max Act: 5.0559. Min Act: -0.1700
Data Index: 6864740 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5247. Min Range: -5.5247
Max Act: 4.9934. Min Act: -0.1700
Data Index: 3554853 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5247. Min Range: -5.5247
Max Act: 4.9934. Min Act: -0.1700
Data Index: 2035998 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5247. Min Range: -5.5247
Max Act: 4.9622. Min Act: -0.1700
Data Index: 2190015 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5247. Min Range: -5.5247
Max Act: 4.9309. Min Act: -0.1700
Data Index: 6962641 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5247. Min Range: -5.5247
Max Act: 4.9309. Min Act: -0.1700
Data Index: 2043867 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5247. Min Range: -5.5247
Max Act: 4.9309. Min Act: -0.1700
Data Index: 5953137 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5247. Min Range: -5.5247
Max Act: 4.8997. Min Act: -0.1700
Data Index: 8559081 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5247. Min Range: -5.5247
Max Act: 4.8997. Min Act: -0.1700
Data Index: 3336847 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5247. Min Range: -5.5247
Max Act: 4.8997. Min Act: -0.1700
Data Index: 6750443 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5247. Min Range: -5.5247
Max Act: 4.8997. Min Act: -0.1700
Data Index: 4942971 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5247. Min Range: -5.5247
Max Act: 4.8997. Min Act: -0.1700
Data Index: 2171051 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19