Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 20 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5259. Min Range: -5.5259
Max Act: 5.5259. Min Act: -0.1700
Data Index: 7268147 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5259. Min Range: -5.5259
Max Act: 5.4634. Min Act: -0.1700
Data Index: 7268148 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5259. Min Range: -5.5259
Max Act: 5.4322. Min Act: -0.1700
Data Index: 1507825 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5259. Min Range: -5.5259
Max Act: 5.4009. Min Act: -0.1700
Data Index: 2205728 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5259. Min Range: -5.5259
Max Act: 5.3697. Min Act: -0.1700
Data Index: 278544 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5259. Min Range: -5.5259
Max Act: 5.2759. Min Act: -0.1700
Data Index: 6369377 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5259. Min Range: -5.5259
Max Act: 5.2447. Min Act: -0.1700
Data Index: 602836 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5259. Min Range: -5.5259
Max Act: 5.1822. Min Act: -0.1700
Data Index: 6369378 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5259. Min Range: -5.5259
Max Act: 4.9634. Min Act: -0.1700
Data Index: 8587986 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5259. Min Range: -5.5259
Max Act: 4.9634. Min Act: -0.1700
Data Index: 8482952 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5259. Min Range: -5.5259
Max Act: 4.9009. Min Act: -0.1700
Data Index: 3473429 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5259. Min Range: -5.5259
Max Act: 4.8697. Min Act: -0.1700
Data Index: 4978312 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5259. Min Range: -5.5259
Max Act: 4.8697. Min Act: -0.1700
Data Index: 7773453 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5259. Min Range: -5.5259
Max Act: 4.8072. Min Act: -0.1700
Data Index: 3510331 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5259. Min Range: -5.5259
Max Act: 4.8072. Min Act: -0.1700
Data Index: 2035189 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5259. Min Range: -5.5259
Max Act: 4.8072. Min Act: -0.1700
Data Index: 2873789 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5259. Min Range: -5.5259
Max Act: 4.7447. Min Act: -0.1700
Data Index: 2136562 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5259. Min Range: -5.5259
Max Act: 4.7759. Min Act: -0.1700
Data Index: 5228128 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5259. Min Range: -5.5259
Max Act: 4.6822. Min Act: -0.1700
Data Index: 5382096 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5259. Min Range: -5.5259
Max Act: 4.7134. Min Act: -0.1700
Data Index: 3284697 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19