Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4388 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3130. Min Range: -5.3130
Max Act: 5.3130. Min Act: -0.1700
Data Index: 3216577 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3130. Min Range: -5.3130
Max Act: 5.3130. Min Act: -0.1700
Data Index: 8561623 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3130. Min Range: -5.3130
Max Act: 5.0942. Min Act: -0.1700
Data Index: 3409017 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3130. Min Range: -5.3130
Max Act: 5.0630. Min Act: -0.1700
Data Index: 1483299 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3130. Min Range: -5.3130
Max Act: 5.0630. Min Act: -0.1700
Data Index: 63401 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3130. Min Range: -5.3130
Max Act: 5.0317. Min Act: -0.1700
Data Index: 1362980 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3130. Min Range: -5.3130
Max Act: 5.0005. Min Act: -0.1700
Data Index: 1459307 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3130. Min Range: -5.3130
Max Act: 4.9692. Min Act: -0.1700
Data Index: 966778 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3130. Min Range: -5.3130
Max Act: 4.9692. Min Act: -0.1700
Data Index: 8599117 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3130. Min Range: -5.3130
Max Act: 5.0005. Min Act: -0.1700
Data Index: 4752493 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3130. Min Range: -5.3130
Max Act: 4.9380. Min Act: -0.1700
Data Index: 8108939 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3130. Min Range: -5.3130
Max Act: 4.9692. Min Act: -0.1700
Data Index: 1825896 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3130. Min Range: -5.3130
Max Act: 4.9380. Min Act: -0.1700
Data Index: 195306 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3130. Min Range: -5.3130
Max Act: 4.9380. Min Act: -0.1700
Data Index: 5418117 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3130. Min Range: -5.3130
Max Act: 4.9380. Min Act: -0.1700
Data Index: 722261 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3130. Min Range: -5.3130
Max Act: 4.9067. Min Act: -0.1700
Data Index: 530851 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3130. Min Range: -5.3130
Max Act: 4.9067. Min Act: -0.1700
Data Index: 8108932 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3130. Min Range: -5.3130
Max Act: 4.9067. Min Act: -0.1700
Data Index: 5599483 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3130. Min Range: -5.3130
Max Act: 4.9067. Min Act: -0.1700
Data Index: 7667711 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3130. Min Range: -5.3130
Max Act: 4.9067. Min Act: -0.1700
Data Index: 7200648 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19