Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 199 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0833. Min Range: -9.0833
Max Act: 9.0833. Min Act: -0.1700
Data Index: 3736918 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0833. Min Range: -9.0833
Max Act: 9.0208. Min Act: -0.1700
Data Index: 921291 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0833. Min Range: -9.0833
Max Act: 8.8333. Min Act: -0.1700
Data Index: 3463795 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0833. Min Range: -9.0833
Max Act: 8.7083. Min Act: -0.1700
Data Index: 5815355 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0833. Min Range: -9.0833
Max Act: 8.6458. Min Act: -0.1700
Data Index: 1941578 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0833. Min Range: -9.0833
Max Act: 8.7083. Min Act: -0.1700
Data Index: 4993356 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0833. Min Range: -9.0833
Max Act: 8.6458. Min Act: -0.1700
Data Index: 1881229 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0833. Min Range: -9.0833
Max Act: 8.5833. Min Act: -0.1700
Data Index: 4933402 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0833. Min Range: -9.0833
Max Act: 8.7083. Min Act: -0.1700
Data Index: 8338261 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0833. Min Range: -9.0833
Max Act: 8.6458. Min Act: -0.1700
Data Index: 7984284 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0833. Min Range: -9.0833
Max Act: 8.6458. Min Act: -0.1700
Data Index: 3859156 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0833. Min Range: -9.0833
Max Act: 8.5833. Min Act: -0.1700
Data Index: 5216043 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0833. Min Range: -9.0833
Max Act: 8.5833. Min Act: -0.1700
Data Index: 3143121 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0833. Min Range: -9.0833
Max Act: 8.5833. Min Act: -0.1700
Data Index: 2794235 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0833. Min Range: -9.0833
Max Act: 8.5833. Min Act: -0.1700
Data Index: 4962927 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0833. Min Range: -9.0833
Max Act: 8.5833. Min Act: -0.1700
Data Index: 1435007 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0833. Min Range: -9.0833
Max Act: 8.5833. Min Act: -0.1700
Data Index: 6066370 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0833. Min Range: -9.0833
Max Act: 8.5833. Min Act: -0.1700
Data Index: 6639143 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0833. Min Range: -9.0833
Max Act: 8.5833. Min Act: -0.1700
Data Index: 5117941 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0833. Min Range: -9.0833
Max Act: 8.5833. Min Act: -0.1700
Data Index: 673145 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #19