Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2592 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2297. Min Range: -5.2297
Max Act: 5.2297. Min Act: -0.1700
Data Index: 4397235 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2297. Min Range: -5.2297
Max Act: 5.1672. Min Act: -0.1700
Data Index: 8010316 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2297. Min Range: -5.2297
Max Act: 5.1672. Min Act: -0.1700
Data Index: 3845284 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2297. Min Range: -5.2297
Max Act: 5.1360. Min Act: -0.1700
Data Index: 6183714 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2297. Min Range: -5.2297
Max Act: 5.1047. Min Act: -0.1700
Data Index: 4588187 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2297. Min Range: -5.2297
Max Act: 5.0735. Min Act: -0.1700
Data Index: 3116855 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2297. Min Range: -5.2297
Max Act: 5.1047. Min Act: -0.1700
Data Index: 5934278 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2297. Min Range: -5.2297
Max Act: 5.0735. Min Act: -0.1700
Data Index: 6324664 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2297. Min Range: -5.2297
Max Act: 4.9797. Min Act: -0.1700
Data Index: 6930213 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2297. Min Range: -5.2297
Max Act: 5.0110. Min Act: -0.1700
Data Index: 6795371 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2297. Min Range: -5.2297
Max Act: 4.9797. Min Act: -0.1700
Data Index: 8515434 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2297. Min Range: -5.2297
Max Act: 4.9797. Min Act: -0.1700
Data Index: 597029 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2297. Min Range: -5.2297
Max Act: 4.9797. Min Act: -0.1700
Data Index: 3948991 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2297. Min Range: -5.2297
Max Act: 5.0110. Min Act: -0.1700
Data Index: 8816358 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2297. Min Range: -5.2297
Max Act: 4.9797. Min Act: -0.1700
Data Index: 180160 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2297. Min Range: -5.2297
Max Act: 4.9797. Min Act: -0.1700
Data Index: 646140 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2297. Min Range: -5.2297
Max Act: 4.9797. Min Act: -0.1700
Data Index: 5117721 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2297. Min Range: -5.2297
Max Act: 4.9797. Min Act: -0.1700
Data Index: 7633874 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2297. Min Range: -5.2297
Max Act: 4.9485. Min Act: -0.1700
Data Index: 5342460 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2297. Min Range: -5.2297
Max Act: 4.9485. Min Act: -0.1700
Data Index: 2517085 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19