Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4224 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.0437. Min Range: -13.0437
Max Act: 13.0437. Min Act: -0.1700
Data Index: 3914267 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.0437. Min Range: -13.0437
Max Act: 12.6687. Min Act: -0.1700
Data Index: 2168149 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.0437. Min Range: -13.0437
Max Act: 12.4812. Min Act: -0.1700
Data Index: 504304 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.0437. Min Range: -13.0437
Max Act: 12.2312. Min Act: -0.1700
Data Index: 287884 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.0437. Min Range: -13.0437
Max Act: 12.2937. Min Act: -0.1700
Data Index: 2390031 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.0437. Min Range: -13.0437
Max Act: 12.2312. Min Act: -0.1700
Data Index: 2949319 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.0437. Min Range: -13.0437
Max Act: 12.2312. Min Act: -0.1700
Data Index: 7608093 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.0437. Min Range: -13.0437
Max Act: 12.2312. Min Act: -0.1700
Data Index: 8210016 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.0437. Min Range: -13.0437
Max Act: 12.1687. Min Act: -0.1700
Data Index: 4448201 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.0437. Min Range: -13.0437
Max Act: 12.2312. Min Act: -0.1700
Data Index: 2567607 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.0437. Min Range: -13.0437
Max Act: 12.1062. Min Act: -0.1700
Data Index: 309985 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.0437. Min Range: -13.0437
Max Act: 12.1062. Min Act: -0.1700
Data Index: 2760997 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.0437. Min Range: -13.0437
Max Act: 12.0437. Min Act: -0.1700
Data Index: 4971876 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.0437. Min Range: -13.0437
Max Act: 12.1062. Min Act: -0.1700
Data Index: 2390030 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.0437. Min Range: -13.0437
Max Act: 12.0437. Min Act: -0.1700
Data Index: 8444358 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.0437. Min Range: -13.0437
Max Act: 11.9812. Min Act: -0.1700
Data Index: 5533298 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.0437. Min Range: -13.0437
Max Act: 11.9812. Min Act: -0.1700
Data Index: 6393408 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.0437. Min Range: -13.0437
Max Act: 11.9812. Min Act: -0.1700
Data Index: 4481911 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.0437. Min Range: -13.0437
Max Act: 11.9812. Min Act: -0.1700
Data Index: 7010998 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.0437. Min Range: -13.0437
Max Act: 11.9187. Min Act: -0.1700
Data Index: 676989 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19