Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1719 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9709. Min Range: -7.9709
Max Act: 7.9709. Min Act: -0.1700
Data Index: 3466769 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9709. Min Range: -7.9709
Max Act: 7.7209. Min Act: -0.1700
Data Index: 7638185 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9709. Min Range: -7.9709
Max Act: 7.4709. Min Act: -0.1700
Data Index: 7294448 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9709. Min Range: -7.9709
Max Act: 7.4397. Min Act: -0.1700
Data Index: 4427707 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9709. Min Range: -7.9709
Max Act: 7.3459. Min Act: -0.1700
Data Index: 6197840 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9709. Min Range: -7.9709
Max Act: 7.3459. Min Act: -0.1700
Data Index: 1659049 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9709. Min Range: -7.9709
Max Act: 7.3147. Min Act: -0.1700
Data Index: 8316895 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9709. Min Range: -7.9709
Max Act: 7.2834. Min Act: -0.1700
Data Index: 6913062 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9709. Min Range: -7.9709
Max Act: 7.2209. Min Act: -0.1700
Data Index: 8252779 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9709. Min Range: -7.9709
Max Act: 7.2522. Min Act: -0.1700
Data Index: 6316780 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9709. Min Range: -7.9709
Max Act: 7.2522. Min Act: -0.1700
Data Index: 8533212 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9709. Min Range: -7.9709
Max Act: 7.2209. Min Act: -0.1700
Data Index: 7375104 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9709. Min Range: -7.9709
Max Act: 7.1897. Min Act: -0.1700
Data Index: 3114221 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9709. Min Range: -7.9709
Max Act: 7.1897. Min Act: -0.1700
Data Index: 8024877 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9709. Min Range: -7.9709
Max Act: 7.1897. Min Act: -0.1700
Data Index: 3577997 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9709. Min Range: -7.9709
Max Act: 7.1897. Min Act: -0.1700
Data Index: 7736797 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9709. Min Range: -7.9709
Max Act: 7.1584. Min Act: -0.1700
Data Index: 878204 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9709. Min Range: -7.9709
Max Act: 7.1272. Min Act: -0.1700
Data Index: 878206 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9709. Min Range: -7.9709
Max Act: 7.1272. Min Act: -0.1700
Data Index: 2479996 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9709. Min Range: -7.9709
Max Act: 7.1272. Min Act: -0.1700
Data Index: 3977275 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19