Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4376 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0407. Min Range: -7.0407
Max Act: 7.0407. Min Act: -0.1700
Data Index: 7136185 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0407. Min Range: -7.0407
Max Act: 6.9469. Min Act: -0.1700
Data Index: 7727501 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0407. Min Range: -7.0407
Max Act: 6.8219. Min Act: -0.1700
Data Index: 2693807 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0407. Min Range: -7.0407
Max Act: 6.8219. Min Act: -0.1700
Data Index: 3991752 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0407. Min Range: -7.0407
Max Act: 6.7907. Min Act: -0.1700
Data Index: 5552149 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0407. Min Range: -7.0407
Max Act: 6.7594. Min Act: -0.1700
Data Index: 1913011 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0407. Min Range: -7.0407
Max Act: 6.6969. Min Act: -0.1700
Data Index: 1620526 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0407. Min Range: -7.0407
Max Act: 6.6969. Min Act: -0.1700
Data Index: 7861808 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0407. Min Range: -7.0407
Max Act: 6.6657. Min Act: -0.1700
Data Index: 2644551 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0407. Min Range: -7.0407
Max Act: 6.6657. Min Act: -0.1700
Data Index: 3181157 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0407. Min Range: -7.0407
Max Act: 6.6344. Min Act: -0.1700
Data Index: 6618354 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0407. Min Range: -7.0407
Max Act: 6.5719. Min Act: -0.1700
Data Index: 7354908 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0407. Min Range: -7.0407
Max Act: 6.5407. Min Act: -0.1700
Data Index: 2478292 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0407. Min Range: -7.0407
Max Act: 6.5407. Min Act: -0.1700
Data Index: 380290 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0407. Min Range: -7.0407
Max Act: 6.5094. Min Act: -0.1700
Data Index: 5913036 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0407. Min Range: -7.0407
Max Act: 6.5094. Min Act: -0.1700
Data Index: 4909469 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0407. Min Range: -7.0407
Max Act: 6.5094. Min Act: -0.1700
Data Index: 567109 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0407. Min Range: -7.0407
Max Act: 6.4782. Min Act: -0.1700
Data Index: 5426025 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0407. Min Range: -7.0407
Max Act: 6.4782. Min Act: -0.1700
Data Index: 3148572 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0407. Min Range: -7.0407
Max Act: 6.4469. Min Act: -0.1700
Data Index: 5564117 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #19