Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 289 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8886. Min Range: -4.8886
Max Act: 4.8886. Min Act: -0.1700
Data Index: 886862 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8886. Min Range: -4.8886
Max Act: 4.7949. Min Act: -0.1700
Data Index: 3553095 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8886. Min Range: -4.8886
Max Act: 4.8261. Min Act: -0.1700
Data Index: 4427362 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8886. Min Range: -4.8886
Max Act: 4.7949. Min Act: -0.1700
Data Index: 3870969 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8886. Min Range: -4.8886
Max Act: 4.7949. Min Act: -0.1700
Data Index: 1088331 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8886. Min Range: -4.8886
Max Act: 4.7324. Min Act: -0.1700
Data Index: 1265079 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8886. Min Range: -4.8886
Max Act: 4.7324. Min Act: -0.1700
Data Index: 4090930 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8886. Min Range: -4.8886
Max Act: 4.7324. Min Act: -0.1700
Data Index: 904332 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8886. Min Range: -4.8886
Max Act: 4.6699. Min Act: -0.1700
Data Index: 1828617 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8886. Min Range: -4.8886
Max Act: 4.6699. Min Act: -0.1700
Data Index: 4396238 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8886. Min Range: -4.8886
Max Act: 4.7011. Min Act: -0.1700
Data Index: 8067002 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8886. Min Range: -4.8886
Max Act: 4.6386. Min Act: -0.1700
Data Index: 7782629 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8886. Min Range: -4.8886
Max Act: 4.6074. Min Act: -0.1700
Data Index: 6681701 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8886. Min Range: -4.8886
Max Act: 4.6386. Min Act: -0.1700
Data Index: 5284037 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8886. Min Range: -4.8886
Max Act: 4.6386. Min Act: -0.1700
Data Index: 3095611 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8886. Min Range: -4.8886
Max Act: 4.6386. Min Act: -0.1700
Data Index: 316971 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8886. Min Range: -4.8886
Max Act: 4.6074. Min Act: -0.1700
Data Index: 6325990 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8886. Min Range: -4.8886
Max Act: 4.6386. Min Act: -0.1700
Data Index: 5430253 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8886. Min Range: -4.8886
Max Act: 4.6074. Min Act: -0.1700
Data Index: 8164381 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8886. Min Range: -4.8886
Max Act: 4.6074. Min Act: -0.1700
Data Index: 2335874 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19