Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3733 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.5749. Min Act: -0.1700
Data Index: 6011553 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.5124. Min Act: -0.1700
Data Index: 8211622 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.4812. Min Act: -0.1700
Data Index: 8636341 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.4187. Min Act: -0.1700
Data Index: 4950017 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.2937. Min Act: -0.1700
Data Index: 1778239 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.2937. Min Act: -0.1700
Data Index: 549924 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.2937. Min Act: -0.1700
Data Index: 6381276 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.2312. Min Act: -0.1700
Data Index: 7736422 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.2624. Min Act: -0.1700
Data Index: 5698266 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.1687. Min Act: -0.1700
Data Index: 2962267 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.1687. Min Act: -0.1700
Data Index: 765621 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.1687. Min Act: -0.1700
Data Index: 473443 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.1687. Min Act: -0.1700
Data Index: 6233879 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.1374. Min Act: -0.1700
Data Index: 3819256 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.1062. Min Act: -0.1700
Data Index: 2770238 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.1062. Min Act: -0.1700
Data Index: 6674861 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.1062. Min Act: -0.1700
Data Index: 1677622 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.1062. Min Act: -0.1700
Data Index: 857660 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.1062. Min Act: -0.1700
Data Index: 5469175 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.1062. Min Act: -0.1700
Data Index: 8521493 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19