Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3824 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6230. Min Range: -5.6230
Max Act: 5.6230. Min Act: -0.1700
Data Index: 127987 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6230. Min Range: -5.6230
Max Act: 5.5918. Min Act: -0.1700
Data Index: 7082374 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6230. Min Range: -5.6230
Max Act: 5.5918. Min Act: -0.1700
Data Index: 2695017 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6230. Min Range: -5.6230
Max Act: 5.5605. Min Act: -0.1700
Data Index: 8331371 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6230. Min Range: -5.6230
Max Act: 5.5293. Min Act: -0.1700
Data Index: 5795631 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6230. Min Range: -5.6230
Max Act: 5.5293. Min Act: -0.1700
Data Index: 7902706 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6230. Min Range: -5.6230
Max Act: 5.4980. Min Act: -0.1700
Data Index: 6631739 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6230. Min Range: -5.6230
Max Act: 5.4980. Min Act: -0.1700
Data Index: 7988824 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6230. Min Range: -5.6230
Max Act: 5.4355. Min Act: -0.1700
Data Index: 7902704 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6230. Min Range: -5.6230
Max Act: 5.4668. Min Act: -0.1700
Data Index: 1687228 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6230. Min Range: -5.6230
Max Act: 5.4668. Min Act: -0.1700
Data Index: 2099523 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6230. Min Range: -5.6230
Max Act: 5.4668. Min Act: -0.1700
Data Index: 201692 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6230. Min Range: -5.6230
Max Act: 5.4668. Min Act: -0.1700
Data Index: 2261773 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6230. Min Range: -5.6230
Max Act: 5.4668. Min Act: -0.1700
Data Index: 3249872 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6230. Min Range: -5.6230
Max Act: 5.4668. Min Act: -0.1700
Data Index: 8117664 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6230. Min Range: -5.6230
Max Act: 5.4668. Min Act: -0.1700
Data Index: 2903989 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6230. Min Range: -5.6230
Max Act: 5.4043. Min Act: -0.1700
Data Index: 5937120 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6230. Min Range: -5.6230
Max Act: 5.4355. Min Act: -0.1700
Data Index: 754346 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6230. Min Range: -5.6230
Max Act: 5.4355. Min Act: -0.1700
Data Index: 6061749 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6230. Min Range: -5.6230
Max Act: 5.4355. Min Act: -0.1700
Data Index: 1950715 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19