Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1001 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7433. Min Range: -6.7433
Max Act: 6.7433. Min Act: -0.1700
Data Index: 3049732 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7433. Min Range: -6.7433
Max Act: 6.6808. Min Act: -0.1700
Data Index: 2562873 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7433. Min Range: -6.7433
Max Act: 6.7120. Min Act: -0.1700
Data Index: 6709744 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7433. Min Range: -6.7433
Max Act: 6.5245. Min Act: -0.1700
Data Index: 3814258 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7433. Min Range: -6.7433
Max Act: 6.3995. Min Act: -0.1700
Data Index: 6993291 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7433. Min Range: -6.7433
Max Act: 6.3370. Min Act: -0.1700
Data Index: 4641981 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7433. Min Range: -6.7433
Max Act: 6.2745. Min Act: -0.1700
Data Index: 4167832 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7433. Min Range: -6.7433
Max Act: 6.3058. Min Act: -0.1700
Data Index: 6490207 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7433. Min Range: -6.7433
Max Act: 6.3058. Min Act: -0.1700
Data Index: 2915701 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7433. Min Range: -6.7433
Max Act: 6.2745. Min Act: -0.1700
Data Index: 4023892 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7433. Min Range: -6.7433
Max Act: 6.2745. Min Act: -0.1700
Data Index: 631660 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7433. Min Range: -6.7433
Max Act: 6.2120. Min Act: -0.1700
Data Index: 4280334 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7433. Min Range: -6.7433
Max Act: 6.1808. Min Act: -0.1700
Data Index: 6482149 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7433. Min Range: -6.7433
Max Act: 6.1495. Min Act: -0.1700
Data Index: 6683806 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7433. Min Range: -6.7433
Max Act: 6.1495. Min Act: -0.1700
Data Index: 8047327 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7433. Min Range: -6.7433
Max Act: 6.1808. Min Act: -0.1700
Data Index: 5332884 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7433. Min Range: -6.7433
Max Act: 6.1495. Min Act: -0.1700
Data Index: 1505241 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7433. Min Range: -6.7433
Max Act: 6.0870. Min Act: -0.1700
Data Index: 7896062 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7433. Min Range: -6.7433
Max Act: 6.1183. Min Act: -0.1700
Data Index: 7077975 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7433. Min Range: -6.7433
Max Act: 6.1183. Min Act: -0.1700
Data Index: 2942069 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #19