Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3899 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5911. Min Range: -6.5911
Max Act: 6.5911. Min Act: -0.1700
Data Index: 2259671 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5911. Min Range: -6.5911
Max Act: 5.9661. Min Act: -0.1700
Data Index: 1402228 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5911. Min Range: -6.5911
Max Act: 5.8723. Min Act: -0.1700
Data Index: 6563393 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5911. Min Range: -6.5911
Max Act: 5.8723. Min Act: -0.1700
Data Index: 3071279 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5911. Min Range: -6.5911
Max Act: 5.8411. Min Act: -0.1700
Data Index: 6683547 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5911. Min Range: -6.5911
Max Act: 5.9036. Min Act: -0.1700
Data Index: 7172991 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5911. Min Range: -6.5911
Max Act: 5.7786. Min Act: -0.1700
Data Index: 8442085 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5911. Min Range: -6.5911
Max Act: 5.8411. Min Act: -0.1700
Data Index: 7476621 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5911. Min Range: -6.5911
Max Act: 5.8098. Min Act: -0.1700
Data Index: 2370548 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5911. Min Range: -6.5911
Max Act: 5.7786. Min Act: -0.1700
Data Index: 2097049 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5911. Min Range: -6.5911
Max Act: 5.7786. Min Act: -0.1700
Data Index: 2223641 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5911. Min Range: -6.5911
Max Act: 5.7473. Min Act: -0.1700
Data Index: 3901830 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5911. Min Range: -6.5911
Max Act: 5.7161. Min Act: -0.1700
Data Index: 6256205 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5911. Min Range: -6.5911
Max Act: 5.7786. Min Act: -0.1700
Data Index: 1795911 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5911. Min Range: -6.5911
Max Act: 5.7161. Min Act: -0.1700
Data Index: 6305312 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5911. Min Range: -6.5911
Max Act: 5.7161. Min Act: -0.1700
Data Index: 7689518 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5911. Min Range: -6.5911
Max Act: 5.6848. Min Act: -0.1700
Data Index: 83009 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5911. Min Range: -6.5911
Max Act: 5.6848. Min Act: -0.1700
Data Index: 4711737 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5911. Min Range: -6.5911
Max Act: 5.6536. Min Act: -0.1700
Data Index: 1798807 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5911. Min Range: -6.5911
Max Act: 5.6536. Min Act: -0.1700
Data Index: 3557661 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #19