Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3813 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8800. Min Range: -7.8800
Max Act: 7.8800. Min Act: -0.1700
Data Index: 691486 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8800. Min Range: -7.8800
Max Act: 7.7237. Min Act: -0.1700
Data Index: 2837918 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8800. Min Range: -7.8800
Max Act: 7.6925. Min Act: -0.1700
Data Index: 1016628 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8800. Min Range: -7.8800
Max Act: 7.6925. Min Act: -0.1700
Data Index: 4919233 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8800. Min Range: -7.8800
Max Act: 7.6612. Min Act: -0.1700
Data Index: 5559809 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8800. Min Range: -7.8800
Max Act: 7.5987. Min Act: -0.1700
Data Index: 5085251 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8800. Min Range: -7.8800
Max Act: 7.5675. Min Act: -0.1700
Data Index: 2021246 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8800. Min Range: -7.8800
Max Act: 7.5362. Min Act: -0.1700
Data Index: 4229123 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8800. Min Range: -7.8800
Max Act: 7.5362. Min Act: -0.1700
Data Index: 8612656 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8800. Min Range: -7.8800
Max Act: 7.4737. Min Act: -0.1700
Data Index: 6849670 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8800. Min Range: -7.8800
Max Act: 7.5050. Min Act: -0.1700
Data Index: 1186316 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8800. Min Range: -7.8800
Max Act: 7.5050. Min Act: -0.1700
Data Index: 7982020 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8800. Min Range: -7.8800
Max Act: 7.4737. Min Act: -0.1700
Data Index: 8220601 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8800. Min Range: -7.8800
Max Act: 7.4737. Min Act: -0.1700
Data Index: 2643713 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8800. Min Range: -7.8800
Max Act: 7.4737. Min Act: -0.1700
Data Index: 2480274 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8800. Min Range: -7.8800
Max Act: 7.4425. Min Act: -0.1700
Data Index: 6157098 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8800. Min Range: -7.8800
Max Act: 7.4112. Min Act: -0.1700
Data Index: 7827720 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8800. Min Range: -7.8800
Max Act: 7.4425. Min Act: -0.1700
Data Index: 4941750 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8800. Min Range: -7.8800
Max Act: 7.4425. Min Act: -0.1700
Data Index: 3847114 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8800. Min Range: -7.8800
Max Act: 7.4425. Min Act: -0.1700
Data Index: 352285 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #19