Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3675 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0714. Min Range: -7.0714
Max Act: 7.0714. Min Act: -0.1700
Data Index: 1557108 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0714. Min Range: -7.0714
Max Act: 7.0089. Min Act: -0.1700
Data Index: 2134332 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0714. Min Range: -7.0714
Max Act: 6.9776. Min Act: -0.1700
Data Index: 2343977 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0714. Min Range: -7.0714
Max Act: 6.9776. Min Act: -0.1700
Data Index: 5672027 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0714. Min Range: -7.0714
Max Act: 6.9776. Min Act: -0.1700
Data Index: 588765 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0714. Min Range: -7.0714
Max Act: 6.9464. Min Act: -0.1700
Data Index: 3575466 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0714. Min Range: -7.0714
Max Act: 6.9464. Min Act: -0.1700
Data Index: 6373150 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0714. Min Range: -7.0714
Max Act: 6.9151. Min Act: -0.1700
Data Index: 932297 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0714. Min Range: -7.0714
Max Act: 6.8839. Min Act: -0.1700
Data Index: 2902352 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0714. Min Range: -7.0714
Max Act: 6.8526. Min Act: -0.1700
Data Index: 4461294 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0714. Min Range: -7.0714
Max Act: 6.8526. Min Act: -0.1700
Data Index: 5063328 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0714. Min Range: -7.0714
Max Act: 6.8526. Min Act: -0.1700
Data Index: 1894071 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0714. Min Range: -7.0714
Max Act: 6.8526. Min Act: -0.1700
Data Index: 4138699 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0714. Min Range: -7.0714
Max Act: 6.8526. Min Act: -0.1700
Data Index: 5966135 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0714. Min Range: -7.0714
Max Act: 6.8214. Min Act: -0.1700
Data Index: 7872374 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0714. Min Range: -7.0714
Max Act: 6.8214. Min Act: -0.1700
Data Index: 6409245 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0714. Min Range: -7.0714
Max Act: 6.8214. Min Act: -0.1700
Data Index: 1149936 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0714. Min Range: -7.0714
Max Act: 6.7901. Min Act: -0.1700
Data Index: 5454049 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0714. Min Range: -7.0714
Max Act: 6.7901. Min Act: -0.1700
Data Index: 1603521 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0714. Min Range: -7.0714
Max Act: 6.7276. Min Act: -0.1700
Data Index: 2156125 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #19