Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2766 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6612. Min Range: -7.6612
Max Act: 7.6612. Min Act: -0.1700
Data Index: 3462289 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6612. Min Range: -7.6612
Max Act: 7.2237. Min Act: -0.1700
Data Index: 3011384 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6612. Min Range: -7.6612
Max Act: 7.1612. Min Act: -0.1700
Data Index: 172432 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6612. Min Range: -7.6612
Max Act: 7.1300. Min Act: -0.1700
Data Index: 4592285 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6612. Min Range: -7.6612
Max Act: 7.0362. Min Act: -0.1700
Data Index: 6084162 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6612. Min Range: -7.6612
Max Act: 7.0362. Min Act: -0.1700
Data Index: 2049664 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6612. Min Range: -7.6612
Max Act: 6.9737. Min Act: -0.1700
Data Index: 277062 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6612. Min Range: -7.6612
Max Act: 6.9112. Min Act: -0.1700
Data Index: 4762787 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6612. Min Range: -7.6612
Max Act: 6.8800. Min Act: -0.1700
Data Index: 5418958 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6612. Min Range: -7.6612
Max Act: 6.8800. Min Act: -0.1700
Data Index: 414850 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6612. Min Range: -7.6612
Max Act: 6.8800. Min Act: -0.1700
Data Index: 8227003 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6612. Min Range: -7.6612
Max Act: 6.8800. Min Act: -0.1700
Data Index: 2004014 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6612. Min Range: -7.6612
Max Act: 6.8487. Min Act: -0.1700
Data Index: 5257087 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6612. Min Range: -7.6612
Max Act: 6.8487. Min Act: -0.1700
Data Index: 2096911 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6612. Min Range: -7.6612
Max Act: 6.8175. Min Act: -0.1700
Data Index: 6081836 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6612. Min Range: -7.6612
Max Act: 6.7862. Min Act: -0.1700
Data Index: 2116163 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6612. Min Range: -7.6612
Max Act: 6.7862. Min Act: -0.1700
Data Index: 6112740 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6612. Min Range: -7.6612
Max Act: 6.7550. Min Act: -0.1700
Data Index: 7687062 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6612. Min Range: -7.6612
Max Act: 6.7550. Min Act: -0.1700
Data Index: 5009177 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6612. Min Range: -7.6612
Max Act: 6.7550. Min Act: -0.1700
Data Index: 4995671 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #19