Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3048 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3727. Min Range: -5.3727
Max Act: 5.3727. Min Act: -0.1700
Data Index: 2997970 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3727. Min Range: -5.3727
Max Act: 5.3102. Min Act: -0.1700
Data Index: 4795107 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3727. Min Range: -5.3727
Max Act: 5.2790. Min Act: -0.1700
Data Index: 1150111 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3727. Min Range: -5.3727
Max Act: 5.2477. Min Act: -0.1700
Data Index: 8669863 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3727. Min Range: -5.3727
Max Act: 5.2165. Min Act: -0.1700
Data Index: 4311078 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3727. Min Range: -5.3727
Max Act: 5.2165. Min Act: -0.1700
Data Index: 1889782 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3727. Min Range: -5.3727
Max Act: 5.1852. Min Act: -0.1700
Data Index: 705260 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3727. Min Range: -5.3727
Max Act: 5.1852. Min Act: -0.1700
Data Index: 1051712 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3727. Min Range: -5.3727
Max Act: 5.1540. Min Act: -0.1700
Data Index: 7469731 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3727. Min Range: -5.3727
Max Act: 5.1540. Min Act: -0.1700
Data Index: 7496670 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3727. Min Range: -5.3727
Max Act: 5.1540. Min Act: -0.1700
Data Index: 1792051 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3727. Min Range: -5.3727
Max Act: 5.1540. Min Act: -0.1700
Data Index: 72427 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3727. Min Range: -5.3727
Max Act: 5.1540. Min Act: -0.1700
Data Index: 2794177 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3727. Min Range: -5.3727
Max Act: 5.0915. Min Act: -0.1700
Data Index: 5730465 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3727. Min Range: -5.3727
Max Act: 5.0915. Min Act: -0.1700
Data Index: 442829 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3727. Min Range: -5.3727
Max Act: 5.0915. Min Act: -0.1700
Data Index: 1051708 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3727. Min Range: -5.3727
Max Act: 5.0915. Min Act: -0.1700
Data Index: 5651541 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3727. Min Range: -5.3727
Max Act: 5.0915. Min Act: -0.1700
Data Index: 5242584 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3727. Min Range: -5.3727
Max Act: 5.0915. Min Act: -0.1700
Data Index: 3120118 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3727. Min Range: -5.3727
Max Act: 5.0290. Min Act: -0.1700
Data Index: 1051707 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #19