Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 887 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0939. Min Range: -7.0939
Max Act: 7.0939. Min Act: -0.1700
Data Index: 5042420 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0939. Min Range: -7.0939
Max Act: 7.0627. Min Act: -0.1700
Data Index: 88663 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0939. Min Range: -7.0939
Max Act: 6.9689. Min Act: -0.1700
Data Index: 7981319 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0939. Min Range: -7.0939
Max Act: 6.9377. Min Act: -0.1700
Data Index: 4909272 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0939. Min Range: -7.0939
Max Act: 6.8127. Min Act: -0.1700
Data Index: 3111890 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0939. Min Range: -7.0939
Max Act: 6.8439. Min Act: -0.1700
Data Index: 3615985 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0939. Min Range: -7.0939
Max Act: 6.8127. Min Act: -0.1700
Data Index: 701005 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0939. Min Range: -7.0939
Max Act: 6.8127. Min Act: -0.1700
Data Index: 2998534 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0939. Min Range: -7.0939
Max Act: 6.8127. Min Act: -0.1700
Data Index: 1873802 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0939. Min Range: -7.0939
Max Act: 6.8127. Min Act: -0.1700
Data Index: 103838 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0939. Min Range: -7.0939
Max Act: 6.7814. Min Act: -0.1700
Data Index: 3427430 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0939. Min Range: -7.0939
Max Act: 6.7814. Min Act: -0.1700
Data Index: 4885089 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0939. Min Range: -7.0939
Max Act: 6.7502. Min Act: -0.1700
Data Index: 2560512 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0939. Min Range: -7.0939
Max Act: 6.7502. Min Act: -0.1700
Data Index: 8736026 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0939. Min Range: -7.0939
Max Act: 6.7189. Min Act: -0.1700
Data Index: 1033040 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0939. Min Range: -7.0939
Max Act: 6.6877. Min Act: -0.1700
Data Index: 6603681 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0939. Min Range: -7.0939
Max Act: 6.6877. Min Act: -0.1700
Data Index: 5917505 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0939. Min Range: -7.0939
Max Act: 6.6877. Min Act: -0.1700
Data Index: 696717 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0939. Min Range: -7.0939
Max Act: 6.6564. Min Act: -0.1700
Data Index: 8334548 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0939. Min Range: -7.0939
Max Act: 6.6564. Min Act: -0.1700
Data Index: 8359205 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19