Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5966 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7582. Min Range: -4.7582
Max Act: 4.7582. Min Act: -0.1700
Data Index: 2880334 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7582. Min Range: -4.7582
Max Act: 4.5395. Min Act: -0.1700
Data Index: 6316418 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7582. Min Range: -4.7582
Max Act: 4.1332. Min Act: -0.1700
Data Index: 6219830 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7582. Min Range: -4.7582
Max Act: 4.1332. Min Act: -0.1700
Data Index: 2581084 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7582. Min Range: -4.7582
Max Act: 4.1020. Min Act: -0.1700
Data Index: 2085942 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7582. Min Range: -4.7582
Max Act: 4.0394. Min Act: -0.1700
Data Index: 3829219 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7582. Min Range: -4.7582
Max Act: 4.0394. Min Act: -0.1700
Data Index: 523529 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7582. Min Range: -4.7582
Max Act: 4.0394. Min Act: -0.1700
Data Index: 7932818 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7582. Min Range: -4.7582
Max Act: 4.0394. Min Act: -0.1700
Data Index: 1417504 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7582. Min Range: -4.7582
Max Act: 3.9769. Min Act: -0.1700
Data Index: 493586 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7582. Min Range: -4.7582
Max Act: 3.9769. Min Act: -0.1700
Data Index: 3677831 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7582. Min Range: -4.7582
Max Act: 3.9769. Min Act: -0.1700
Data Index: 158928 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7582. Min Range: -4.7582
Max Act: 3.9144. Min Act: -0.1700
Data Index: 4929235 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7582. Min Range: -4.7582
Max Act: 3.9769. Min Act: -0.1700
Data Index: 2489488 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7582. Min Range: -4.7582
Max Act: 3.9457. Min Act: -0.1700
Data Index: 7720203 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7582. Min Range: -4.7582
Max Act: 3.9144. Min Act: -0.1700
Data Index: 2904887 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7582. Min Range: -4.7582
Max Act: 3.9144. Min Act: -0.1700
Data Index: 575757 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7582. Min Range: -4.7582
Max Act: 3.8831. Min Act: -0.1700
Data Index: 4799896 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7582. Min Range: -4.7582
Max Act: 3.8831. Min Act: -0.1700
Data Index: 2173039 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7582. Min Range: -4.7582
Max Act: 3.8831. Min Act: -0.1700
Data Index: 21975 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19