Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2675 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4703. Min Range: -8.4703
Max Act: 8.4703. Min Act: -0.1700
Data Index: 10307 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4703. Min Range: -8.4703
Max Act: 8.0328. Min Act: -0.1700
Data Index: 7750242 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4703. Min Range: -8.4703
Max Act: 7.8765. Min Act: -0.1700
Data Index: 7146769 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4703. Min Range: -8.4703
Max Act: 7.7828. Min Act: -0.1700
Data Index: 7201075 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4703. Min Range: -8.4703
Max Act: 7.5328. Min Act: -0.1700
Data Index: 4159421 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4703. Min Range: -8.4703
Max Act: 7.4078. Min Act: -0.1700
Data Index: 1414390 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4703. Min Range: -8.4703
Max Act: 7.3453. Min Act: -0.1700
Data Index: 5053611 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4703. Min Range: -8.4703
Max Act: 7.3140. Min Act: -0.1700
Data Index: 2960889 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4703. Min Range: -8.4703
Max Act: 7.3453. Min Act: -0.1700
Data Index: 5593975 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4703. Min Range: -8.4703
Max Act: 7.3140. Min Act: -0.1700
Data Index: 4675731 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4703. Min Range: -8.4703
Max Act: 7.1578. Min Act: -0.1700
Data Index: 4642782 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4703. Min Range: -8.4703
Max Act: 7.1578. Min Act: -0.1700
Data Index: 8680583 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4703. Min Range: -8.4703
Max Act: 7.0953. Min Act: -0.1700
Data Index: 5609953 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4703. Min Range: -8.4703
Max Act: 7.0640. Min Act: -0.1700
Data Index: 8365497 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4703. Min Range: -8.4703
Max Act: 7.0328. Min Act: -0.1700
Data Index: 2863620 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4703. Min Range: -8.4703
Max Act: 7.0640. Min Act: -0.1700
Data Index: 4692116 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4703. Min Range: -8.4703
Max Act: 7.0015. Min Act: -0.1700
Data Index: 5553973 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4703. Min Range: -8.4703
Max Act: 7.0015. Min Act: -0.1700
Data Index: 8296992 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4703. Min Range: -8.4703
Max Act: 6.9703. Min Act: -0.1700
Data Index: 4020139 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4703. Min Range: -8.4703
Max Act: 6.9703. Min Act: -0.1700
Data Index: 7421689 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19