Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5871 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1485. Min Range: -6.1485
Max Act: 6.1485. Min Act: -0.1700
Data Index: 6958716 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1485. Min Range: -6.1485
Max Act: 6.1485. Min Act: -0.1700
Data Index: 192344 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1485. Min Range: -6.1485
Max Act: 6.1485. Min Act: -0.1700
Data Index: 1542756 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1485. Min Range: -6.1485
Max Act: 6.1173. Min Act: -0.1700
Data Index: 5059202 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1485. Min Range: -6.1485
Max Act: 6.1173. Min Act: -0.1700
Data Index: 8102414 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1485. Min Range: -6.1485
Max Act: 6.1173. Min Act: -0.1700
Data Index: 1140021 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1485. Min Range: -6.1485
Max Act: 6.0860. Min Act: -0.1700
Data Index: 3512049 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1485. Min Range: -6.1485
Max Act: 6.0548. Min Act: -0.1700
Data Index: 4162895 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1485. Min Range: -6.1485
Max Act: 6.0235. Min Act: -0.1700
Data Index: 4761194 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1485. Min Range: -6.1485
Max Act: 6.0235. Min Act: -0.1700
Data Index: 6922359 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1485. Min Range: -6.1485
Max Act: 6.0235. Min Act: -0.1700
Data Index: 1046667 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1485. Min Range: -6.1485
Max Act: 6.0235. Min Act: -0.1700
Data Index: 5514596 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1485. Min Range: -6.1485
Max Act: 5.9923. Min Act: -0.1700
Data Index: 2605132 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1485. Min Range: -6.1485
Max Act: 6.0548. Min Act: -0.1700
Data Index: 7557772 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1485. Min Range: -6.1485
Max Act: 6.0235. Min Act: -0.1700
Data Index: 4859094 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1485. Min Range: -6.1485
Max Act: 5.9610. Min Act: -0.1700
Data Index: 279245 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1485. Min Range: -6.1485
Max Act: 5.9923. Min Act: -0.1700
Data Index: 1899605 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1485. Min Range: -6.1485
Max Act: 5.9610. Min Act: -0.1700
Data Index: 5057756 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1485. Min Range: -6.1485
Max Act: 5.9610. Min Act: -0.1700
Data Index: 6141312 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1485. Min Range: -6.1485
Max Act: 5.9610. Min Act: -0.1700
Data Index: 7941520 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19