Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3072 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5590. Min Range: -5.5590
Max Act: 5.5590. Min Act: -0.1700
Data Index: 3281809 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5590. Min Range: -5.5590
Max Act: 5.4340. Min Act: -0.1700
Data Index: 7110505 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5590. Min Range: -5.5590
Max Act: 5.3402. Min Act: -0.1700
Data Index: 2927074 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5590. Min Range: -5.5590
Max Act: 5.3090. Min Act: -0.1700
Data Index: 5495023 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5590. Min Range: -5.5590
Max Act: 5.3090. Min Act: -0.1700
Data Index: 2927072 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5590. Min Range: -5.5590
Max Act: 5.2777. Min Act: -0.1700
Data Index: 3281807 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5590. Min Range: -5.5590
Max Act: 5.2465. Min Act: -0.1700
Data Index: 2927073 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5590. Min Range: -5.5590
Max Act: 5.2152. Min Act: -0.1700
Data Index: 2927069 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5590. Min Range: -5.5590
Max Act: 5.2152. Min Act: -0.1700
Data Index: 2927071 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5590. Min Range: -5.5590
Max Act: 5.2152. Min Act: -0.1700
Data Index: 1957766 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5590. Min Range: -5.5590
Max Act: 5.2152. Min Act: -0.1700
Data Index: 607578 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5590. Min Range: -5.5590
Max Act: 5.2152. Min Act: -0.1700
Data Index: 3723463 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5590. Min Range: -5.5590
Max Act: 5.1527. Min Act: -0.1700
Data Index: 5510276 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5590. Min Range: -5.5590
Max Act: 5.1215. Min Act: -0.1700
Data Index: 3723456 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5590. Min Range: -5.5590
Max Act: 5.1215. Min Act: -0.1700
Data Index: 6611005 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5590. Min Range: -5.5590
Max Act: 5.0902. Min Act: -0.1700
Data Index: 3281806 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5590. Min Range: -5.5590
Max Act: 5.0902. Min Act: -0.1700
Data Index: 3723466 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5590. Min Range: -5.5590
Max Act: 5.0590. Min Act: -0.1700
Data Index: 2927070 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5590. Min Range: -5.5590
Max Act: 5.0902. Min Act: -0.1700
Data Index: 3723453 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5590. Min Range: -5.5590
Max Act: 5.0590. Min Act: -0.1700
Data Index: 3281808 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19