Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2861 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.5723. Min Act: -0.1700
Data Index: 3369671 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.5411. Min Act: -0.1700
Data Index: 7287164 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.4161. Min Act: -0.1700
Data Index: 1038839 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.3848. Min Act: -0.1700
Data Index: 6755262 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.2911. Min Act: -0.1700
Data Index: 70973 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.1973. Min Act: -0.1700
Data Index: 346622 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.1348. Min Act: -0.1700
Data Index: 7650744 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.1348. Min Act: -0.1700
Data Index: 3934068 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.1348. Min Act: -0.1700
Data Index: 6451034 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.0723. Min Act: -0.1700
Data Index: 745749 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.0411. Min Act: -0.1700
Data Index: 5833579 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.0723. Min Act: -0.1700
Data Index: 4391622 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.0411. Min Act: -0.1700
Data Index: 3946941 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.0411. Min Act: -0.1700
Data Index: 3946942 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.0411. Min Act: -0.1700
Data Index: 5906672 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.0411. Min Act: -0.1700
Data Index: 3193498 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.0098. Min Act: -0.1700
Data Index: 8077588 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.0098. Min Act: -0.1700
Data Index: 7525667 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.0098. Min Act: -0.1700
Data Index: 2939156 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5723. Min Range: -6.5723
Max Act: 6.0411. Min Act: -0.1700
Data Index: 3508451 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19