Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 50 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4328. Min Range: -6.4328
Max Act: 6.4328. Min Act: -0.1700
Data Index: 2481969 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4328. Min Range: -6.4328
Max Act: 6.1516. Min Act: -0.1700
Data Index: 6042380 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4328. Min Range: -6.4328
Max Act: 6.0578. Min Act: -0.1700
Data Index: 6775090 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4328. Min Range: -6.4328
Max Act: 6.0266. Min Act: -0.1700
Data Index: 3458753 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4328. Min Range: -6.4328
Max Act: 5.9016. Min Act: -0.1700
Data Index: 4058311 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4328. Min Range: -6.4328
Max Act: 5.8078. Min Act: -0.1700
Data Index: 2764763 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4328. Min Range: -6.4328
Max Act: 5.8078. Min Act: -0.1700
Data Index: 1290581 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4328. Min Range: -6.4328
Max Act: 5.8078. Min Act: -0.1700
Data Index: 7759140 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4328. Min Range: -6.4328
Max Act: 5.7453. Min Act: -0.1700
Data Index: 8602278 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4328. Min Range: -6.4328
Max Act: 5.7453. Min Act: -0.1700
Data Index: 6895732 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4328. Min Range: -6.4328
Max Act: 5.7453. Min Act: -0.1700
Data Index: 4614166 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4328. Min Range: -6.4328
Max Act: 5.7453. Min Act: -0.1700
Data Index: 1995790 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4328. Min Range: -6.4328
Max Act: 5.7141. Min Act: -0.1700
Data Index: 6885941 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4328. Min Range: -6.4328
Max Act: 5.6828. Min Act: -0.1700
Data Index: 3846174 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4328. Min Range: -6.4328
Max Act: 5.6828. Min Act: -0.1700
Data Index: 30395 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4328. Min Range: -6.4328
Max Act: 5.6516. Min Act: -0.1700
Data Index: 6625673 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4328. Min Range: -6.4328
Max Act: 5.6516. Min Act: -0.1700
Data Index: 2857430 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4328. Min Range: -6.4328
Max Act: 5.6516. Min Act: -0.1700
Data Index: 4437943 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4328. Min Range: -6.4328
Max Act: 5.6203. Min Act: -0.1700
Data Index: 8097071 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4328. Min Range: -6.4328
Max Act: 5.6203. Min Act: -0.1700
Data Index: 8471208 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #19