Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6350 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5546. Min Range: -3.5546
Max Act: 3.5546. Min Act: -0.1700
Data Index: 7851571 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5546. Min Range: -3.5546
Max Act: 3.5076. Min Act: -0.1700
Data Index: 452180 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5546. Min Range: -3.5546
Max Act: 3.4293. Min Act: -0.1700
Data Index: 4748977 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5546. Min Range: -3.5546
Max Act: 3.4136. Min Act: -0.1700
Data Index: 2403662 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5546. Min Range: -3.5546
Max Act: 3.3822. Min Act: -0.1700
Data Index: 6112722 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5546. Min Range: -3.5546
Max Act: 3.3509. Min Act: -0.1700
Data Index: 7795050 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5546. Min Range: -3.5546
Max Act: 3.3665. Min Act: -0.1700
Data Index: 4498937 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5546. Min Range: -3.5546
Max Act: 3.3665. Min Act: -0.1700
Data Index: 5634288 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5546. Min Range: -3.5546
Max Act: 3.3352. Min Act: -0.1700
Data Index: 6367914 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5546. Min Range: -3.5546
Max Act: 3.3352. Min Act: -0.1700
Data Index: 3875789 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5546. Min Range: -3.5546
Max Act: 3.3352. Min Act: -0.1700
Data Index: 1276920 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5546. Min Range: -3.5546
Max Act: 3.3509. Min Act: -0.1700
Data Index: 6164106 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5546. Min Range: -3.5546
Max Act: 3.3195. Min Act: -0.1700
Data Index: 2756484 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5546. Min Range: -3.5546
Max Act: 3.3195. Min Act: -0.1700
Data Index: 3516344 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5546. Min Range: -3.5546
Max Act: 3.3195. Min Act: -0.1700
Data Index: 2871400 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5546. Min Range: -3.5546
Max Act: 3.3038. Min Act: -0.1700
Data Index: 1885847 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5546. Min Range: -3.5546
Max Act: 3.3038. Min Act: -0.1700
Data Index: 2463558 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5546. Min Range: -3.5546
Max Act: 3.2881. Min Act: -0.1700
Data Index: 8028965 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5546. Min Range: -3.5546
Max Act: 3.2881. Min Act: -0.1700
Data Index: 3819706 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5546. Min Range: -3.5546
Max Act: 3.2881. Min Act: -0.1700
Data Index: 4479342 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19