Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3121 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6689. Min Range: -8.6689
Max Act: 8.6689. Min Act: -0.1700
Data Index: 4928393 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6689. Min Range: -8.6689
Max Act: 7.7314. Min Act: -0.1700
Data Index: 8389655 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6689. Min Range: -8.6689
Max Act: 7.6689. Min Act: -0.1700
Data Index: 6956442 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6689. Min Range: -8.6689
Max Act: 7.6689. Min Act: -0.1700
Data Index: 2016185 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6689. Min Range: -8.6689
Max Act: 7.6689. Min Act: -0.1700
Data Index: 1919457 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6689. Min Range: -8.6689
Max Act: 7.6689. Min Act: -0.1700
Data Index: 4753865 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6689. Min Range: -8.6689
Max Act: 7.6689. Min Act: -0.1700
Data Index: 7407911 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6689. Min Range: -8.6689
Max Act: 7.6689. Min Act: -0.1700
Data Index: 1295260 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6689. Min Range: -8.6689
Max Act: 7.6064. Min Act: -0.1700
Data Index: 7397721 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6689. Min Range: -8.6689
Max Act: 7.6064. Min Act: -0.1700
Data Index: 1047154 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6689. Min Range: -8.6689
Max Act: 7.6064. Min Act: -0.1700
Data Index: 3494675 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6689. Min Range: -8.6689
Max Act: 7.5439. Min Act: -0.1700
Data Index: 1317229 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6689. Min Range: -8.6689
Max Act: 7.5439. Min Act: -0.1700
Data Index: 157894 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6689. Min Range: -8.6689
Max Act: 7.4814. Min Act: -0.1700
Data Index: 5823253 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6689. Min Range: -8.6689
Max Act: 7.4502. Min Act: -0.1700
Data Index: 3761124 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6689. Min Range: -8.6689
Max Act: 7.4814. Min Act: -0.1700
Data Index: 6385521 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6689. Min Range: -8.6689
Max Act: 7.4814. Min Act: -0.1700
Data Index: 617859 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6689. Min Range: -8.6689
Max Act: 7.4814. Min Act: -0.1700
Data Index: 2057182 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6689. Min Range: -8.6689
Max Act: 7.4814. Min Act: -0.1700
Data Index: 346218 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6689. Min Range: -8.6689
Max Act: 7.4814. Min Act: -0.1700
Data Index: 1774862 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #19