Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4030 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.4388. Min Act: -0.1700
Data Index: 269979 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.3450. Min Act: -0.1700
Data Index: 39564 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.2825. Min Act: -0.1700
Data Index: 2583200 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.2512. Min Act: -0.1700
Data Index: 7890533 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.2512. Min Act: -0.1700
Data Index: 1666335 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.1887. Min Act: -0.1700
Data Index: 6062571 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.2200. Min Act: -0.1700
Data Index: 6728713 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.2200. Min Act: -0.1700
Data Index: 3898916 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.1887. Min Act: -0.1700
Data Index: 1215609 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.1887. Min Act: -0.1700
Data Index: 8721598 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.1262. Min Act: -0.1700
Data Index: 1240994 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.1575. Min Act: -0.1700
Data Index: 8789870 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.1575. Min Act: -0.1700
Data Index: 6167862 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.0950. Min Act: -0.1700
Data Index: 7552618 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.1262. Min Act: -0.1700
Data Index: 1074024 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.1262. Min Act: -0.1700
Data Index: 8053336 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.1262. Min Act: -0.1700
Data Index: 770742 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.0950. Min Act: -0.1700
Data Index: 1144475 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.1262. Min Act: -0.1700
Data Index: 2781439 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.1262. Min Act: -0.1700
Data Index: 5988091 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #19