Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 901 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5639. Min Range: -3.5639
Max Act: 3.5639. Min Act: -0.1700
Data Index: 3392913 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5639. Min Range: -3.5639
Max Act: 3.5013. Min Act: -0.1700
Data Index: 660462 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5639. Min Range: -3.5639
Max Act: 3.5013. Min Act: -0.1700
Data Index: 1849335 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5639. Min Range: -3.5639
Max Act: 3.5326. Min Act: -0.1699
Data Index: 26974 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5639. Min Range: -3.5639
Max Act: 3.5013. Min Act: -0.1700
Data Index: 643826 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5639. Min Range: -3.5639
Max Act: 3.4386. Min Act: -0.1700
Data Index: 6575520 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5639. Min Range: -3.5639
Max Act: 3.4699. Min Act: -0.1700
Data Index: 5453384 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5639. Min Range: -3.5639
Max Act: 3.4699. Min Act: -0.1700
Data Index: 1228810 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5639. Min Range: -3.5639
Max Act: 3.4386. Min Act: -0.1700
Data Index: 7622827 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5639. Min Range: -3.5639
Max Act: 3.4699. Min Act: -0.1700
Data Index: 2679174 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5639. Min Range: -3.5639
Max Act: 3.4386. Min Act: -0.1700
Data Index: 4624110 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5639. Min Range: -3.5639
Max Act: 3.4072. Min Act: -0.1700
Data Index: 5381101 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5639. Min Range: -3.5639
Max Act: 3.4072. Min Act: -0.1700
Data Index: 6823821 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5639. Min Range: -3.5639
Max Act: 3.4072. Min Act: -0.1700
Data Index: 4768980 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5639. Min Range: -3.5639
Max Act: 3.4072. Min Act: -0.1700
Data Index: 5808812 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5639. Min Range: -3.5639
Max Act: 3.4072. Min Act: -0.1700
Data Index: 1735246 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5639. Min Range: -3.5639
Max Act: 3.3759. Min Act: -0.1700
Data Index: 7092725 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5639. Min Range: -3.5639
Max Act: 3.3759. Min Act: -0.1700
Data Index: 2396022 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5639. Min Range: -3.5639
Max Act: 3.3759. Min Act: -0.1700
Data Index: 664756 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5639. Min Range: -3.5639
Max Act: 3.3602. Min Act: -0.1700
Data Index: 3858203 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19