Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2832 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8827. Min Range: -7.8827
Max Act: 7.8827. Min Act: -0.1700
Data Index: 8163424 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8827. Min Range: -7.8827
Max Act: 7.7890. Min Act: -0.1700
Data Index: 1969277 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8827. Min Range: -7.8827
Max Act: 7.7265. Min Act: -0.1700
Data Index: 5317899 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8827. Min Range: -7.8827
Max Act: 7.6952. Min Act: -0.1700
Data Index: 3793772 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8827. Min Range: -7.8827
Max Act: 7.6952. Min Act: -0.1700
Data Index: 3731944 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8827. Min Range: -7.8827
Max Act: 7.6015. Min Act: -0.1700
Data Index: 4081620 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8827. Min Range: -7.8827
Max Act: 7.6327. Min Act: -0.1700
Data Index: 4433476 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8827. Min Range: -7.8827
Max Act: 7.5702. Min Act: -0.1700
Data Index: 4123948 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8827. Min Range: -7.8827
Max Act: 7.5077. Min Act: -0.1700
Data Index: 3026689 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8827. Min Range: -7.8827
Max Act: 7.4765. Min Act: -0.1700
Data Index: 2290470 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8827. Min Range: -7.8827
Max Act: 7.4765. Min Act: -0.1700
Data Index: 4776276 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8827. Min Range: -7.8827
Max Act: 7.4140. Min Act: -0.1700
Data Index: 3662753 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8827. Min Range: -7.8827
Max Act: 7.4140. Min Act: -0.1700
Data Index: 34576 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8827. Min Range: -7.8827
Max Act: 7.3827. Min Act: -0.1700
Data Index: 7299615 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8827. Min Range: -7.8827
Max Act: 7.3827. Min Act: -0.1700
Data Index: 5957848 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8827. Min Range: -7.8827
Max Act: 7.4140. Min Act: -0.1700
Data Index: 7938639 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8827. Min Range: -7.8827
Max Act: 7.3202. Min Act: -0.1700
Data Index: 4425022 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8827. Min Range: -7.8827
Max Act: 7.3515. Min Act: -0.1700
Data Index: 5073461 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8827. Min Range: -7.8827
Max Act: 7.3202. Min Act: -0.1700
Data Index: 2226049 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8827. Min Range: -7.8827
Max Act: 7.3202. Min Act: -0.1700
Data Index: 4362936 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19