Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 852 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7118. Min Range: -9.7118
Max Act: 9.7118. Min Act: -0.1700
Data Index: 2862774 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7118. Min Range: -9.7118
Max Act: 9.5243. Min Act: -0.1700
Data Index: 7034797 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7118. Min Range: -9.7118
Max Act: 9.5243. Min Act: -0.1700
Data Index: 5635735 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7118. Min Range: -9.7118
Max Act: 9.5243. Min Act: -0.1700
Data Index: 1102627 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7118. Min Range: -9.7118
Max Act: 9.3993. Min Act: -0.1700
Data Index: 2271809 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7118. Min Range: -9.7118
Max Act: 9.4618. Min Act: -0.1700
Data Index: 316738 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7118. Min Range: -9.7118
Max Act: 9.3993. Min Act: -0.1700
Data Index: 1911780 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7118. Min Range: -9.7118
Max Act: 9.3368. Min Act: -0.1700
Data Index: 4532278 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7118. Min Range: -9.7118
Max Act: 9.3368. Min Act: -0.1700
Data Index: 1279321 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7118. Min Range: -9.7118
Max Act: 9.2743. Min Act: -0.1700
Data Index: 4675138 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7118. Min Range: -9.7118
Max Act: 9.2743. Min Act: -0.1700
Data Index: 8078739 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7118. Min Range: -9.7118
Max Act: 9.1493. Min Act: -0.1700
Data Index: 1250131 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7118. Min Range: -9.7118
Max Act: 9.2118. Min Act: -0.1700
Data Index: 494929 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7118. Min Range: -9.7118
Max Act: 9.1493. Min Act: -0.1699
Data Index: 2968553 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7118. Min Range: -9.7118
Max Act: 9.2118. Min Act: -0.1700
Data Index: 6782564 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7118. Min Range: -9.7118
Max Act: 9.2118. Min Act: -0.1700
Data Index: 1725464 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7118. Min Range: -9.7118
Max Act: 9.2118. Min Act: -0.1700
Data Index: 4604385 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7118. Min Range: -9.7118
Max Act: 9.2118. Min Act: -0.1700
Data Index: 6910732 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7118. Min Range: -9.7118
Max Act: 9.1493. Min Act: -0.1700
Data Index: 1274661 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7118. Min Range: -9.7118
Max Act: 9.1493. Min Act: -0.1700
Data Index: 1470311 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #19