Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2917 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4749. Min Range: -5.4749
Max Act: 5.4749. Min Act: -0.1700
Data Index: 1294593 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4749. Min Range: -5.4749
Max Act: 5.4124. Min Act: -0.1700
Data Index: 3351052 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4749. Min Range: -5.4749
Max Act: 5.4124. Min Act: -0.1700
Data Index: 2713016 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4749. Min Range: -5.4749
Max Act: 5.3499. Min Act: -0.1700
Data Index: 4790371 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4749. Min Range: -5.4749
Max Act: 5.3811. Min Act: -0.1700
Data Index: 5022981 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4749. Min Range: -5.4749
Max Act: 5.3499. Min Act: -0.1700
Data Index: 6392247 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4749. Min Range: -5.4749
Max Act: 5.3186. Min Act: -0.1700
Data Index: 3562414 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4749. Min Range: -5.4749
Max Act: 5.2874. Min Act: -0.1700
Data Index: 4606266 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4749. Min Range: -5.4749
Max Act: 5.2874. Min Act: -0.1700
Data Index: 7203403 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4749. Min Range: -5.4749
Max Act: 5.2874. Min Act: -0.1700
Data Index: 396770 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4749. Min Range: -5.4749
Max Act: 5.2874. Min Act: -0.1700
Data Index: 260345 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4749. Min Range: -5.4749
Max Act: 5.2874. Min Act: -0.1700
Data Index: 45048 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4749. Min Range: -5.4749
Max Act: 5.2874. Min Act: -0.1700
Data Index: 7747540 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4749. Min Range: -5.4749
Max Act: 5.2561. Min Act: -0.1700
Data Index: 1135157 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4749. Min Range: -5.4749
Max Act: 5.2561. Min Act: -0.1700
Data Index: 5847597 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4749. Min Range: -5.4749
Max Act: 5.2561. Min Act: -0.1700
Data Index: 6335407 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4749. Min Range: -5.4749
Max Act: 5.2561. Min Act: -0.1700
Data Index: 3508576 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4749. Min Range: -5.4749
Max Act: 5.2561. Min Act: -0.1700
Data Index: 805386 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4749. Min Range: -5.4749
Max Act: 5.2561. Min Act: -0.1700
Data Index: 1948978 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4749. Min Range: -5.4749
Max Act: 5.2561. Min Act: -0.1700
Data Index: 3325045 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19