Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3934 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2548. Min Range: -7.2548
Max Act: 7.2548. Min Act: -0.1700
Data Index: 765814 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2548. Min Range: -7.2548
Max Act: 7.0360. Min Act: -0.1700
Data Index: 4004256 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2548. Min Range: -7.2548
Max Act: 7.0048. Min Act: -0.1700
Data Index: 720148 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2548. Min Range: -7.2548
Max Act: 7.0048. Min Act: -0.1700
Data Index: 7315930 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2548. Min Range: -7.2548
Max Act: 6.9423. Min Act: -0.1700
Data Index: 694739 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2548. Min Range: -7.2548
Max Act: 6.9423. Min Act: -0.1700
Data Index: 6700215 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2548. Min Range: -7.2548
Max Act: 6.9110. Min Act: -0.1700
Data Index: 4914610 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2548. Min Range: -7.2548
Max Act: 6.8798. Min Act: -0.1700
Data Index: 612157 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2548. Min Range: -7.2548
Max Act: 6.8798. Min Act: -0.1700
Data Index: 5019201 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2548. Min Range: -7.2548
Max Act: 6.8798. Min Act: -0.1700
Data Index: 4261903 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2548. Min Range: -7.2548
Max Act: 6.8798. Min Act: -0.1700
Data Index: 7225114 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2548. Min Range: -7.2548
Max Act: 6.8173. Min Act: -0.1700
Data Index: 3035824 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2548. Min Range: -7.2548
Max Act: 6.8173. Min Act: -0.1700
Data Index: 8019330 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2548. Min Range: -7.2548
Max Act: 6.8173. Min Act: -0.1700
Data Index: 4895903 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2548. Min Range: -7.2548
Max Act: 6.7860. Min Act: -0.1700
Data Index: 3753984 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2548. Min Range: -7.2548
Max Act: 6.7548. Min Act: -0.1700
Data Index: 315463 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2548. Min Range: -7.2548
Max Act: 6.7235. Min Act: -0.1700
Data Index: 5324816 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2548. Min Range: -7.2548
Max Act: 6.7548. Min Act: -0.1700
Data Index: 6088094 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2548. Min Range: -7.2548
Max Act: 6.7235. Min Act: -0.1700
Data Index: 4951319 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2548. Min Range: -7.2548
Max Act: 6.6923. Min Act: -0.1700
Data Index: 6847980 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19