Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1361 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4054. Min Range: -8.4054
Max Act: 8.4054. Min Act: -0.1700
Data Index: 3611999 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4054. Min Range: -8.4054
Max Act: 8.3741. Min Act: -0.1700
Data Index: 8207319 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4054. Min Range: -8.4054
Max Act: 7.8741. Min Act: -0.1700
Data Index: 7026681 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4054. Min Range: -8.4054
Max Act: 7.8429. Min Act: -0.1700
Data Index: 3928244 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4054. Min Range: -8.4054
Max Act: 7.8116. Min Act: -0.1700
Data Index: 8763471 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4054. Min Range: -8.4054
Max Act: 7.7804. Min Act: -0.1700
Data Index: 8636209 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4054. Min Range: -8.4054
Max Act: 7.6866. Min Act: -0.1700
Data Index: 7603547 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4054. Min Range: -8.4054
Max Act: 7.6241. Min Act: -0.1700
Data Index: 7157230 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4054. Min Range: -8.4054
Max Act: 7.5929. Min Act: -0.1700
Data Index: 1292811 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4054. Min Range: -8.4054
Max Act: 7.6241. Min Act: -0.1700
Data Index: 3435395 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4054. Min Range: -8.4054
Max Act: 7.5929. Min Act: -0.1700
Data Index: 8396675 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4054. Min Range: -8.4054
Max Act: 7.5616. Min Act: -0.1700
Data Index: 3410420 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4054. Min Range: -8.4054
Max Act: 7.5616. Min Act: -0.1700
Data Index: 5871074 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4054. Min Range: -8.4054
Max Act: 7.5929. Min Act: -0.1700
Data Index: 307849 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4054. Min Range: -8.4054
Max Act: 7.5616. Min Act: -0.1700
Data Index: 8154357 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4054. Min Range: -8.4054
Max Act: 7.5304. Min Act: -0.1700
Data Index: 4990163 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4054. Min Range: -8.4054
Max Act: 7.4991. Min Act: -0.1700
Data Index: 13869 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4054. Min Range: -8.4054
Max Act: 7.4991. Min Act: -0.1700
Data Index: 3951312 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4054. Min Range: -8.4054
Max Act: 7.4991. Min Act: -0.1700
Data Index: 6531392 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4054. Min Range: -8.4054
Max Act: 7.4991. Min Act: -0.1700
Data Index: 2532163 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19