Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3457 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6582. Min Range: -7.6582
Max Act: 7.6582. Min Act: -0.1700
Data Index: 6399687 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6582. Min Range: -7.6582
Max Act: 7.3457. Min Act: -0.1700
Data Index: 681800 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6582. Min Range: -7.6582
Max Act: 7.2832. Min Act: -0.1700
Data Index: 4031485 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6582. Min Range: -7.6582
Max Act: 7.0644. Min Act: -0.1700
Data Index: 6998653 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6582. Min Range: -7.6582
Max Act: 7.0644. Min Act: -0.1700
Data Index: 4015848 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6582. Min Range: -7.6582
Max Act: 6.9707. Min Act: -0.1700
Data Index: 6299923 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6582. Min Range: -7.6582
Max Act: 6.9707. Min Act: -0.1700
Data Index: 7005316 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6582. Min Range: -7.6582
Max Act: 6.9394. Min Act: -0.1700
Data Index: 5639981 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6582. Min Range: -7.6582
Max Act: 6.8769. Min Act: -0.1700
Data Index: 6921740 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6582. Min Range: -7.6582
Max Act: 6.8457. Min Act: -0.1700
Data Index: 726396 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6582. Min Range: -7.6582
Max Act: 6.8144. Min Act: -0.1700
Data Index: 4508160 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6582. Min Range: -7.6582
Max Act: 6.7519. Min Act: -0.1700
Data Index: 3896262 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6582. Min Range: -7.6582
Max Act: 6.7207. Min Act: -0.1700
Data Index: 972324 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6582. Min Range: -7.6582
Max Act: 6.6894. Min Act: -0.1700
Data Index: 2132174 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6582. Min Range: -7.6582
Max Act: 6.6894. Min Act: -0.1700
Data Index: 5588541 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6582. Min Range: -7.6582
Max Act: 6.6894. Min Act: -0.1700
Data Index: 8116956 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6582. Min Range: -7.6582
Max Act: 6.6894. Min Act: -0.1700
Data Index: 3485813 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6582. Min Range: -7.6582
Max Act: 6.6582. Min Act: -0.1700
Data Index: 7654851 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6582. Min Range: -7.6582
Max Act: 6.6582. Min Act: -0.1700
Data Index: 4941187 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6582. Min Range: -7.6582
Max Act: 6.6269. Min Act: -0.1700
Data Index: 1969141 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #19