Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3550 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4960. Min Range: -7.4960
Max Act: 7.4960. Min Act: -0.1700
Data Index: 1233342 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4960. Min Range: -7.4960
Max Act: 7.3085. Min Act: -0.1700
Data Index: 3632291 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4960. Min Range: -7.4960
Max Act: 7.2460. Min Act: -0.1700
Data Index: 7451769 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4960. Min Range: -7.4960
Max Act: 7.1210. Min Act: -0.1700
Data Index: 3098763 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4960. Min Range: -7.4960
Max Act: 7.1523. Min Act: -0.1700
Data Index: 7629392 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4960. Min Range: -7.4960
Max Act: 7.1523. Min Act: -0.1700
Data Index: 6779268 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4960. Min Range: -7.4960
Max Act: 7.0585. Min Act: -0.1700
Data Index: 4896759 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4960. Min Range: -7.4960
Max Act: 7.0898. Min Act: -0.1700
Data Index: 7048156 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4960. Min Range: -7.4960
Max Act: 6.9960. Min Act: -0.1700
Data Index: 2103874 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4960. Min Range: -7.4960
Max Act: 6.9960. Min Act: -0.1700
Data Index: 230873 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4960. Min Range: -7.4960
Max Act: 6.9335. Min Act: -0.1700
Data Index: 681647 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4960. Min Range: -7.4960
Max Act: 6.9648. Min Act: -0.1700
Data Index: 4381116 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4960. Min Range: -7.4960
Max Act: 6.9335. Min Act: -0.1700
Data Index: 5444435 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4960. Min Range: -7.4960
Max Act: 6.9648. Min Act: -0.1700
Data Index: 5394194 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4960. Min Range: -7.4960
Max Act: 6.8398. Min Act: -0.1700
Data Index: 3084085 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4960. Min Range: -7.4960
Max Act: 6.8398. Min Act: -0.1700
Data Index: 4771728 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4960. Min Range: -7.4960
Max Act: 6.8398. Min Act: -0.1700
Data Index: 7661008 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4960. Min Range: -7.4960
Max Act: 6.7773. Min Act: -0.1700
Data Index: 1879325 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4960. Min Range: -7.4960
Max Act: 6.7773. Min Act: -0.1700
Data Index: 2318068 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4960. Min Range: -7.4960
Max Act: 6.7773. Min Act: -0.1700
Data Index: 3606018 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #19