Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2016 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4707. Min Range: -8.4707
Max Act: 8.4707. Min Act: -0.1700
Data Index: 1014456 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4707. Min Range: -8.4707
Max Act: 8.3457. Min Act: -0.1700
Data Index: 4373180 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4707. Min Range: -8.4707
Max Act: 8.2207. Min Act: -0.1700
Data Index: 1788639 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4707. Min Range: -8.4707
Max Act: 8.1270. Min Act: -0.1700
Data Index: 2998661 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4707. Min Range: -8.4707
Max Act: 8.0020. Min Act: -0.1700
Data Index: 824096 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4707. Min Range: -8.4707
Max Act: 8.0020. Min Act: -0.1700
Data Index: 5578486 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4707. Min Range: -8.4707
Max Act: 7.8457. Min Act: -0.1700
Data Index: 3846670 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4707. Min Range: -8.4707
Max Act: 7.8145. Min Act: -0.1700
Data Index: 8428615 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4707. Min Range: -8.4707
Max Act: 7.7832. Min Act: -0.1700
Data Index: 1970824 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4707. Min Range: -8.4707
Max Act: 7.7520. Min Act: -0.1700
Data Index: 7238606 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4707. Min Range: -8.4707
Max Act: 7.7520. Min Act: -0.1700
Data Index: 7680810 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4707. Min Range: -8.4707
Max Act: 7.7520. Min Act: -0.1700
Data Index: 8696145 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4707. Min Range: -8.4707
Max Act: 7.7520. Min Act: -0.1700
Data Index: 4387059 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4707. Min Range: -8.4707
Max Act: 7.7207. Min Act: -0.1700
Data Index: 2190480 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4707. Min Range: -8.4707
Max Act: 7.7207. Min Act: -0.1700
Data Index: 3790902 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4707. Min Range: -8.4707
Max Act: 7.6895. Min Act: -0.1700
Data Index: 1385090 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4707. Min Range: -8.4707
Max Act: 7.7207. Min Act: -0.1700
Data Index: 2084144 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4707. Min Range: -8.4707
Max Act: 7.6895. Min Act: -0.1700
Data Index: 7800997 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4707. Min Range: -8.4707
Max Act: 7.6895. Min Act: -0.1700
Data Index: 3453157 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4707. Min Range: -8.4707
Max Act: 7.6582. Min Act: -0.1700
Data Index: 169799 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19