Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2145 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.0050. Min Range: -2.0050
Max Act: 2.0050. Min Act: -0.1700
Data Index: 4155879 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0050. Min Range: -2.0050
Max Act: 1.9966. Min Act: -0.1700
Data Index: 6302512 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0050. Min Range: -2.0050
Max Act: 2.0050. Min Act: -0.1691
Data Index: 1957622 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0050. Min Range: -2.0050
Max Act: 1.9881. Min Act: -0.1700
Data Index: 2104502 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0050. Min Range: -2.0050
Max Act: 1.9797. Min Act: -0.1700
Data Index: 275608 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0050. Min Range: -2.0050
Max Act: 1.9797. Min Act: -0.1700
Data Index: 7722685 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0050. Min Range: -2.0050
Max Act: 1.9712. Min Act: -0.1700
Data Index: 911206 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0050. Min Range: -2.0050
Max Act: 1.9542. Min Act: -0.1699
Data Index: 6676142 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0050. Min Range: -2.0050
Max Act: 1.9457. Min Act: -0.1700
Data Index: 5583337 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0050. Min Range: -2.0050
Max Act: 1.9457. Min Act: -0.1700
Data Index: 6167834 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0050. Min Range: -2.0050
Max Act: 1.9287. Min Act: -0.1700
Data Index: 911207 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0050. Min Range: -2.0050
Max Act: 1.9117. Min Act: -0.1699
Data Index: 1011302 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0050. Min Range: -2.0050
Max Act: 1.9202. Min Act: -0.1697
Data Index: 5585739 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0050. Min Range: -2.0050
Max Act: 1.9032. Min Act: -0.1700
Data Index: 2915897 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0050. Min Range: -2.0050
Max Act: 1.9032. Min Act: -0.1700
Data Index: 124071 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0050. Min Range: -2.0050
Max Act: 1.9032. Min Act: -0.1699
Data Index: 2030524 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0050. Min Range: -2.0050
Max Act: 1.9032. Min Act: -0.1700
Data Index: 5263926 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0050. Min Range: -2.0050
Max Act: 1.8947. Min Act: -0.1699
Data Index: 4222058 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0050. Min Range: -2.0050
Max Act: 1.8947. Min Act: -0.1699
Data Index: 6394403 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0050. Min Range: -2.0050
Max Act: 1.8861. Min Act: -0.1700
Data Index: 1007538 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19