Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2883 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9814. Min Range: -9.9814
Max Act: 9.9814. Min Act: -0.1700
Data Index: 7820055 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9814. Min Range: -9.9814
Max Act: 9.6689. Min Act: -0.1700
Data Index: 3234680 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9814. Min Range: -9.9814
Max Act: 9.6064. Min Act: -0.1700
Data Index: 6213557 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9814. Min Range: -9.9814
Max Act: 9.4814. Min Act: -0.1700
Data Index: 5184277 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9814. Min Range: -9.9814
Max Act: 9.5439. Min Act: -0.1700
Data Index: 4331920 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9814. Min Range: -9.9814
Max Act: 9.4814. Min Act: -0.1700
Data Index: 3352599 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9814. Min Range: -9.9814
Max Act: 9.4814. Min Act: -0.1700
Data Index: 4127268 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9814. Min Range: -9.9814
Max Act: 9.4814. Min Act: -0.1700
Data Index: 2150295 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9814. Min Range: -9.9814
Max Act: 9.4814. Min Act: -0.1700
Data Index: 4012937 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9814. Min Range: -9.9814
Max Act: 9.4814. Min Act: -0.1700
Data Index: 6579104 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9814. Min Range: -9.9814
Max Act: 9.4189. Min Act: -0.1700
Data Index: 7184881 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9814. Min Range: -9.9814
Max Act: 9.4189. Min Act: -0.1700
Data Index: 6658843 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9814. Min Range: -9.9814
Max Act: 9.4814. Min Act: -0.1700
Data Index: 1911907 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9814. Min Range: -9.9814
Max Act: 9.4189. Min Act: -0.1700
Data Index: 5388351 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9814. Min Range: -9.9814
Max Act: 9.4189. Min Act: -0.1700
Data Index: 661128 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9814. Min Range: -9.9814
Max Act: 9.3564. Min Act: -0.1700
Data Index: 810382 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9814. Min Range: -9.9814
Max Act: 9.4189. Min Act: -0.1700
Data Index: 6565426 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9814. Min Range: -9.9814
Max Act: 9.4189. Min Act: -0.1700
Data Index: 3352600 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9814. Min Range: -9.9814
Max Act: 9.3564. Min Act: -0.1700
Data Index: 5298863 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9814. Min Range: -9.9814
Max Act: 9.2939. Min Act: -0.1700
Data Index: 2280250 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19