Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2269 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1743. Min Range: -8.1743
Max Act: 8.1743. Min Act: -0.1700
Data Index: 6163798 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1743. Min Range: -8.1743
Max Act: 7.7368. Min Act: -0.1700
Data Index: 407171 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1743. Min Range: -8.1743
Max Act: 7.6743. Min Act: -0.1700
Data Index: 5587618 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1743. Min Range: -8.1743
Max Act: 7.5806. Min Act: -0.1700
Data Index: 2971062 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1743. Min Range: -8.1743
Max Act: 7.4243. Min Act: -0.1700
Data Index: 4345130 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1743. Min Range: -8.1743
Max Act: 7.2993. Min Act: -0.1700
Data Index: 8010918 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1743. Min Range: -8.1743
Max Act: 7.2368. Min Act: -0.1700
Data Index: 2671187 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1743. Min Range: -8.1743
Max Act: 7.2368. Min Act: -0.1700
Data Index: 6163787 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1743. Min Range: -8.1743
Max Act: 7.2368. Min Act: -0.1700
Data Index: 477918 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1743. Min Range: -8.1743
Max Act: 7.2056. Min Act: -0.1700
Data Index: 7374090 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1743. Min Range: -8.1743
Max Act: 7.2056. Min Act: -0.1700
Data Index: 3264296 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1743. Min Range: -8.1743
Max Act: 7.2056. Min Act: -0.1700
Data Index: 8261540 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1743. Min Range: -8.1743
Max Act: 7.1431. Min Act: -0.1700
Data Index: 5846372 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1743. Min Range: -8.1743
Max Act: 7.1743. Min Act: -0.1700
Data Index: 72982 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1743. Min Range: -8.1743
Max Act: 7.1743. Min Act: -0.1700
Data Index: 1947575 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1743. Min Range: -8.1743
Max Act: 7.1431. Min Act: -0.1700
Data Index: 2140843 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1743. Min Range: -8.1743
Max Act: 7.1431. Min Act: -0.1700
Data Index: 4062188 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1743. Min Range: -8.1743
Max Act: 7.1118. Min Act: -0.1700
Data Index: 7697316 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1743. Min Range: -8.1743
Max Act: 7.1118. Min Act: -0.1700
Data Index: 8418958 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1743. Min Range: -8.1743
Max Act: 7.1118. Min Act: -0.1700
Data Index: 1090670 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19