Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3248 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2558. Min Range: -7.2558
Max Act: 7.2558. Min Act: -0.1700
Data Index: 3561852 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2558. Min Range: -7.2558
Max Act: 7.1933. Min Act: -0.1700
Data Index: 7189204 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2558. Min Range: -7.2558
Max Act: 7.2558. Min Act: -0.1700
Data Index: 3561833 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2558. Min Range: -7.2558
Max Act: 7.1933. Min Act: -0.1700
Data Index: 5124878 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2558. Min Range: -7.2558
Max Act: 7.0683. Min Act: -0.1700
Data Index: 6459252 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2558. Min Range: -7.2558
Max Act: 7.0683. Min Act: -0.1700
Data Index: 5994101 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2558. Min Range: -7.2558
Max Act: 7.0058. Min Act: -0.1700
Data Index: 5124889 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2558. Min Range: -7.2558
Max Act: 7.0370. Min Act: -0.1700
Data Index: 8489695 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2558. Min Range: -7.2558
Max Act: 6.9745. Min Act: -0.1700
Data Index: 216147 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2558. Min Range: -7.2558
Max Act: 6.9120. Min Act: -0.1700
Data Index: 686325 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2558. Min Range: -7.2558
Max Act: 6.9433. Min Act: -0.1700
Data Index: 5147901 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2558. Min Range: -7.2558
Max Act: 6.8808. Min Act: -0.1700
Data Index: 6465445 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2558. Min Range: -7.2558
Max Act: 6.8495. Min Act: -0.1700
Data Index: 3021362 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2558. Min Range: -7.2558
Max Act: 6.8183. Min Act: -0.1700
Data Index: 8265102 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2558. Min Range: -7.2558
Max Act: 6.8495. Min Act: -0.1700
Data Index: 6040427 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2558. Min Range: -7.2558
Max Act: 6.8183. Min Act: -0.1700
Data Index: 2920541 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2558. Min Range: -7.2558
Max Act: 6.8183. Min Act: -0.1700
Data Index: 972669 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2558. Min Range: -7.2558
Max Act: 6.7870. Min Act: -0.1700
Data Index: 7791066 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2558. Min Range: -7.2558
Max Act: 6.7870. Min Act: -0.1700
Data Index: 6459256 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2558. Min Range: -7.2558
Max Act: 6.7870. Min Act: -0.1700
Data Index: 3820699 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #19