Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2870 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2690. Min Range: -6.2690
Max Act: 6.2690. Min Act: -0.1700
Data Index: 2563865 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2690. Min Range: -6.2690
Max Act: 6.2065. Min Act: -0.1700
Data Index: 1508906 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2690. Min Range: -6.2690
Max Act: 6.0815. Min Act: -0.1700
Data Index: 1968393 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2690. Min Range: -6.2690
Max Act: 6.0190. Min Act: -0.1700
Data Index: 6059676 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2690. Min Range: -6.2690
Max Act: 5.9253. Min Act: -0.1700
Data Index: 2804547 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2690. Min Range: -6.2690
Max Act: 5.9253. Min Act: -0.1700
Data Index: 1968394 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2690. Min Range: -6.2690
Max Act: 5.8940. Min Act: -0.1700
Data Index: 2338610 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2690. Min Range: -6.2690
Max Act: 5.8940. Min Act: -0.1700
Data Index: 5907109 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2690. Min Range: -6.2690
Max Act: 5.8940. Min Act: -0.1700
Data Index: 3732542 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2690. Min Range: -6.2690
Max Act: 5.8940. Min Act: -0.1700
Data Index: 4740370 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2690. Min Range: -6.2690
Max Act: 5.8628. Min Act: -0.1700
Data Index: 4023076 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2690. Min Range: -6.2690
Max Act: 5.7690. Min Act: -0.1700
Data Index: 4965357 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2690. Min Range: -6.2690
Max Act: 5.7065. Min Act: -0.1700
Data Index: 3095365 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2690. Min Range: -6.2690
Max Act: 5.7378. Min Act: -0.1700
Data Index: 5907110 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2690. Min Range: -6.2690
Max Act: 5.6753. Min Act: -0.1700
Data Index: 658329 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2690. Min Range: -6.2690
Max Act: 5.6753. Min Act: -0.1700
Data Index: 5556958 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2690. Min Range: -6.2690
Max Act: 5.6753. Min Act: -0.1700
Data Index: 6175078 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2690. Min Range: -6.2690
Max Act: 5.5815. Min Act: -0.1700
Data Index: 8338774 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2690. Min Range: -6.2690
Max Act: 5.6128. Min Act: -0.1700
Data Index: 6254347 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2690. Min Range: -6.2690
Max Act: 5.5815. Min Act: -0.1700
Data Index: 2513660 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19