Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5441 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1244. Min Range: -4.1244
Max Act: 4.1244. Min Act: -0.1700
Data Index: 2385871 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1244. Min Range: -4.1244
Max Act: 4.1244. Min Act: -0.1700
Data Index: 235189 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1244. Min Range: -4.1244
Max Act: 4.1244. Min Act: -0.1700
Data Index: 1234164 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1244. Min Range: -4.1244
Max Act: 4.1244. Min Act: -0.1700
Data Index: 759610 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1244. Min Range: -4.1244
Max Act: 4.0931. Min Act: -0.1700
Data Index: 3442991 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1244. Min Range: -4.1244
Max Act: 4.0931. Min Act: -0.1700
Data Index: 2329477 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1244. Min Range: -4.1244
Max Act: 4.0931. Min Act: -0.1700
Data Index: 1335072 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1244. Min Range: -4.1244
Max Act: 4.0931. Min Act: -0.1700
Data Index: 2074030 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1244. Min Range: -4.1244
Max Act: 4.0931. Min Act: -0.1700
Data Index: 1851349 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1244. Min Range: -4.1244
Max Act: 4.0931. Min Act: -0.1700
Data Index: 6968986 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1244. Min Range: -4.1244
Max Act: 4.1244. Min Act: -0.1700
Data Index: 6022324 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1244. Min Range: -4.1244
Max Act: 4.0931. Min Act: -0.1700
Data Index: 3885542 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1244. Min Range: -4.1244
Max Act: 4.0931. Min Act: -0.1700
Data Index: 3609117 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1244. Min Range: -4.1244
Max Act: 4.0931. Min Act: -0.1700
Data Index: 3000687 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1244. Min Range: -4.1244
Max Act: 4.0619. Min Act: -0.1700
Data Index: 301668 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1244. Min Range: -4.1244
Max Act: 4.0619. Min Act: -0.1700
Data Index: 1322591 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1244. Min Range: -4.1244
Max Act: 4.0619. Min Act: -0.1700
Data Index: 2383260 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1244. Min Range: -4.1244
Max Act: 4.0619. Min Act: -0.1700
Data Index: 358500 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1244. Min Range: -4.1244
Max Act: 4.0619. Min Act: -0.1700
Data Index: 965697 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1244. Min Range: -4.1244
Max Act: 4.0619. Min Act: -0.1700
Data Index: 2413907 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19