Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 68 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.7792. Min Act: -0.1700
Data Index: 1292684 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.7480. Min Act: -0.1700
Data Index: 4790994 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.4042. Min Act: -0.1700
Data Index: 92725 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.3730. Min Act: -0.1700
Data Index: 5874667 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.3417. Min Act: -0.1700
Data Index: 2984359 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.3417. Min Act: -0.1700
Data Index: 6872483 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.3105. Min Act: -0.1700
Data Index: 1685146 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.2792. Min Act: -0.1700
Data Index: 6658147 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.2480. Min Act: -0.1700
Data Index: 2281112 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.2167. Min Act: -0.1700
Data Index: 4776568 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.2167. Min Act: -0.1700
Data Index: 7419905 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.2167. Min Act: -0.1700
Data Index: 4828299 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.1855. Min Act: -0.1700
Data Index: 1536294 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.1542. Min Act: -0.1700
Data Index: 4209349 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.1542. Min Act: -0.1700
Data Index: 2024038 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.1230. Min Act: -0.1700
Data Index: 6130108 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.0917. Min Act: -0.1700
Data Index: 748518 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.1230. Min Act: -0.1700
Data Index: 4242829 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.0917. Min Act: -0.1700
Data Index: 1774216 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7792. Min Range: -5.7792
Max Act: 5.0917. Min Act: -0.1700
Data Index: 2128933 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #19