Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4022 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7850. Min Range: -4.7850
Max Act: 4.7850. Min Act: -0.1700
Data Index: 1379429 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7850. Min Range: -4.7850
Max Act: 4.7538. Min Act: -0.1700
Data Index: 1241735 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7850. Min Range: -4.7850
Max Act: 4.7225. Min Act: -0.1700
Data Index: 5750706 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7850. Min Range: -4.7850
Max Act: 4.6913. Min Act: -0.1700
Data Index: 8146502 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7850. Min Range: -4.7850
Max Act: 4.7225. Min Act: -0.1700
Data Index: 8592616 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7850. Min Range: -4.7850
Max Act: 4.6913. Min Act: -0.1700
Data Index: 8580808 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7850. Min Range: -4.7850
Max Act: 4.6600. Min Act: -0.1700
Data Index: 7889030 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7850. Min Range: -4.7850
Max Act: 4.6600. Min Act: -0.1700
Data Index: 1046490 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7850. Min Range: -4.7850
Max Act: 4.5975. Min Act: -0.1700
Data Index: 326264 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7850. Min Range: -4.7850
Max Act: 4.5975. Min Act: -0.1700
Data Index: 1988380 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7850. Min Range: -4.7850
Max Act: 4.5663. Min Act: -0.1700
Data Index: 355990 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7850. Min Range: -4.7850
Max Act: 4.5663. Min Act: -0.1700
Data Index: 4417858 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7850. Min Range: -4.7850
Max Act: 4.5663. Min Act: -0.1700
Data Index: 1854881 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7850. Min Range: -4.7850
Max Act: 4.5350. Min Act: -0.1700
Data Index: 6505568 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7850. Min Range: -4.7850
Max Act: 4.5350. Min Act: -0.1700
Data Index: 8726333 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7850. Min Range: -4.7850
Max Act: 4.5350. Min Act: -0.1700
Data Index: 6903995 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7850. Min Range: -4.7850
Max Act: 4.5350. Min Act: -0.1700
Data Index: 7842391 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7850. Min Range: -4.7850
Max Act: 4.5350. Min Act: -0.1700
Data Index: 6163832 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7850. Min Range: -4.7850
Max Act: 4.5663. Min Act: -0.1700
Data Index: 74507 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7850. Min Range: -4.7850
Max Act: 4.5038. Min Act: -0.1700
Data Index: 3748810 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19