Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4494 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5989. Min Range: -7.5989
Max Act: 7.5989. Min Act: -0.1700
Data Index: 5334025 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5989. Min Range: -7.5989
Max Act: 7.5364. Min Act: -0.1700
Data Index: 874740 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5989. Min Range: -7.5989
Max Act: 7.4114. Min Act: -0.1700
Data Index: 529208 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5989. Min Range: -7.5989
Max Act: 7.4739. Min Act: -0.1700
Data Index: 2574821 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5989. Min Range: -7.5989
Max Act: 7.3801. Min Act: -0.1700
Data Index: 3599123 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5989. Min Range: -7.5989
Max Act: 7.3801. Min Act: -0.1700
Data Index: 7868964 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5989. Min Range: -7.5989
Max Act: 7.2864. Min Act: -0.1700
Data Index: 1750333 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5989. Min Range: -7.5989
Max Act: 7.2864. Min Act: -0.1700
Data Index: 4224422 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5989. Min Range: -7.5989
Max Act: 7.2864. Min Act: -0.1700
Data Index: 5246793 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5989. Min Range: -7.5989
Max Act: 7.2551. Min Act: -0.1700
Data Index: 5925621 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5989. Min Range: -7.5989
Max Act: 7.2551. Min Act: -0.1700
Data Index: 8207143 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5989. Min Range: -7.5989
Max Act: 7.2239. Min Act: -0.1700
Data Index: 2168184 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5989. Min Range: -7.5989
Max Act: 7.0989. Min Act: -0.1700
Data Index: 2508987 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5989. Min Range: -7.5989
Max Act: 7.1301. Min Act: -0.1700
Data Index: 7401204 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5989. Min Range: -7.5989
Max Act: 7.0676. Min Act: -0.1700
Data Index: 7067652 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5989. Min Range: -7.5989
Max Act: 7.0364. Min Act: -0.1700
Data Index: 7347782 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5989. Min Range: -7.5989
Max Act: 7.0364. Min Act: -0.1700
Data Index: 3649221 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5989. Min Range: -7.5989
Max Act: 7.0051. Min Act: -0.1700
Data Index: 1829346 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5989. Min Range: -7.5989
Max Act: 7.0051. Min Act: -0.1700
Data Index: 5687068 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5989. Min Range: -7.5989
Max Act: 7.0051. Min Act: -0.1700
Data Index: 1736723 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19