Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1816 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8842. Min Range: -9.8842
Max Act: 9.8842. Min Act: -0.1700
Data Index: 8099294 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8842. Min Range: -9.8842
Max Act: 9.1342. Min Act: -0.1700
Data Index: 4585295 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8842. Min Range: -9.8842
Max Act: 9.0717. Min Act: -0.1700
Data Index: 1550888 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8842. Min Range: -9.8842
Max Act: 9.0717. Min Act: -0.1700
Data Index: 8787406 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8842. Min Range: -9.8842
Max Act: 9.0717. Min Act: -0.1700
Data Index: 2136204 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8842. Min Range: -9.8842
Max Act: 9.0092. Min Act: -0.1700
Data Index: 3913948 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8842. Min Range: -9.8842
Max Act: 8.8217. Min Act: -0.1700
Data Index: 3258014 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8842. Min Range: -9.8842
Max Act: 8.8842. Min Act: -0.1700
Data Index: 2846419 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8842. Min Range: -9.8842
Max Act: 8.8842. Min Act: -0.1700
Data Index: 6198238 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8842. Min Range: -9.8842
Max Act: 8.8217. Min Act: -0.1700
Data Index: 4147626 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8842. Min Range: -9.8842
Max Act: 8.8217. Min Act: -0.1700
Data Index: 4000677 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8842. Min Range: -9.8842
Max Act: 8.7592. Min Act: -0.1700
Data Index: 2352919 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8842. Min Range: -9.8842
Max Act: 8.7592. Min Act: -0.1700
Data Index: 1118808 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8842. Min Range: -9.8842
Max Act: 8.6967. Min Act: -0.1700
Data Index: 5861951 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8842. Min Range: -9.8842
Max Act: 8.6967. Min Act: -0.1700
Data Index: 3136837 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8842. Min Range: -9.8842
Max Act: 8.6967. Min Act: -0.1700
Data Index: 855483 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8842. Min Range: -9.8842
Max Act: 8.6967. Min Act: -0.1700
Data Index: 1522913 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8842. Min Range: -9.8842
Max Act: 8.6342. Min Act: -0.1700
Data Index: 7663434 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8842. Min Range: -9.8842
Max Act: 8.6967. Min Act: -0.1700
Data Index: 1759880 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8842. Min Range: -9.8842
Max Act: 8.6342. Min Act: -0.1700
Data Index: 2976709 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #19