Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1279 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5526. Min Range: -5.5526
Max Act: 5.5526. Min Act: -0.1700
Data Index: 5088055 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5526. Min Range: -5.5526
Max Act: 5.5214. Min Act: -0.1700
Data Index: 4950981 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5526. Min Range: -5.5526
Max Act: 5.4901. Min Act: -0.1700
Data Index: 1193241 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5526. Min Range: -5.5526
Max Act: 5.4901. Min Act: -0.1700
Data Index: 3407297 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5526. Min Range: -5.5526
Max Act: 5.4276. Min Act: -0.1700
Data Index: 2191652 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5526. Min Range: -5.5526
Max Act: 5.4276. Min Act: -0.1700
Data Index: 2215860 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5526. Min Range: -5.5526
Max Act: 5.2714. Min Act: -0.1700
Data Index: 1149411 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5526. Min Range: -5.5526
Max Act: 5.2401. Min Act: -0.1700
Data Index: 5323456 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5526. Min Range: -5.5526
Max Act: 5.2401. Min Act: -0.1700
Data Index: 2652437 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5526. Min Range: -5.5526
Max Act: 5.2401. Min Act: -0.1700
Data Index: 8123861 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5526. Min Range: -5.5526
Max Act: 5.2401. Min Act: -0.1700
Data Index: 8140908 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5526. Min Range: -5.5526
Max Act: 5.2401. Min Act: -0.1700
Data Index: 6205380 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5526. Min Range: -5.5526
Max Act: 5.1776. Min Act: -0.1700
Data Index: 2373549 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5526. Min Range: -5.5526
Max Act: 5.1464. Min Act: -0.1700
Data Index: 1873179 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5526. Min Range: -5.5526
Max Act: 5.1464. Min Act: -0.1700
Data Index: 7140952 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5526. Min Range: -5.5526
Max Act: 5.1464. Min Act: -0.1700
Data Index: 743462 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5526. Min Range: -5.5526
Max Act: 5.1464. Min Act: -0.1700
Data Index: 2015413 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5526. Min Range: -5.5526
Max Act: 5.1464. Min Act: -0.1700
Data Index: 7849790 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5526. Min Range: -5.5526
Max Act: 5.1464. Min Act: -0.1700
Data Index: 3077754 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5526. Min Range: -5.5526
Max Act: 5.1776. Min Act: -0.1700
Data Index: 2557335 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19