Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2616 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.7265. Min Range: -1.7265
Max Act: 1.7265. Min Act: -0.1693
Data Index: 2130687 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7265. Min Range: -1.7265
Max Act: 1.7092. Min Act: -0.1686
Data Index: 2130690 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7265. Min Range: -1.7265
Max Act: 1.3942. Min Act: -0.1700
Data Index: 2094998 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7265. Min Range: -1.7265
Max Act: 1.3589. Min Act: -0.1700
Data Index: 6399628 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7265. Min Range: -1.7265
Max Act: 1.3413. Min Act: -0.1699
Data Index: 8743632 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7265. Min Range: -1.7265
Max Act: 1.3236. Min Act: -0.1700
Data Index: 4083741 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7265. Min Range: -1.7265
Max Act: 1.2707. Min Act: -0.1699
Data Index: 6399632 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7265. Min Range: -1.7265
Max Act: 1.2707. Min Act: -0.1700
Data Index: 2130694 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7265. Min Range: -1.7265
Max Act: 1.2531. Min Act: -0.1699
Data Index: 2095002 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7265. Min Range: -1.7265
Max Act: 1.2531. Min Act: -0.1700
Data Index: 6399634 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7265. Min Range: -1.7265
Max Act: 1.2531. Min Act: -0.1699
Data Index: 6242642 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7265. Min Range: -1.7265
Max Act: 1.2354. Min Act: -0.1700
Data Index: 2846231 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7265. Min Range: -1.7265
Max Act: 1.2002. Min Act: -0.1698
Data Index: 7378867 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7265. Min Range: -1.7265
Max Act: 1.2002. Min Act: -0.1699
Data Index: 6399629 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7265. Min Range: -1.7265
Max Act: 1.2178. Min Act: -0.1700
Data Index: 3333492 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7265. Min Range: -1.7265
Max Act: 1.2354. Min Act: -0.1696
Data Index: 5774344 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7265. Min Range: -1.7265
Max Act: 1.1826. Min Act: -0.1700
Data Index: 1925413 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7265. Min Range: -1.7265
Max Act: 1.1826. Min Act: -0.1692
Data Index: 6519709 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7265. Min Range: -1.7265
Max Act: 1.1650. Min Act: -0.1692
Data Index: 6399635 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7265. Min Range: -1.7265
Max Act: 1.1826. Min Act: -0.1697
Data Index: 2130688 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19