Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3438 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8903. Min Range: -5.8903
Max Act: 5.8903. Min Act: -0.1700
Data Index: 1789897 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8903. Min Range: -5.8903
Max Act: 5.7341. Min Act: -0.1700
Data Index: 4381273 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8903. Min Range: -5.8903
Max Act: 5.5778. Min Act: -0.1700
Data Index: 3010713 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8903. Min Range: -5.8903
Max Act: 5.5466. Min Act: -0.1700
Data Index: 6822051 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8903. Min Range: -5.8903
Max Act: 5.5466. Min Act: -0.1700
Data Index: 1935852 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8903. Min Range: -5.8903
Max Act: 5.5778. Min Act: -0.1700
Data Index: 6109532 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8903. Min Range: -5.8903
Max Act: 5.5153. Min Act: -0.1700
Data Index: 6899185 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8903. Min Range: -5.8903
Max Act: 5.5153. Min Act: -0.1700
Data Index: 748486 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8903. Min Range: -5.8903
Max Act: 5.5153. Min Act: -0.1700
Data Index: 6122185 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8903. Min Range: -5.8903
Max Act: 5.5153. Min Act: -0.1700
Data Index: 1797402 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8903. Min Range: -5.8903
Max Act: 5.5153. Min Act: -0.1698
Data Index: 4765746 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8903. Min Range: -5.8903
Max Act: 5.4528. Min Act: -0.1700
Data Index: 5922012 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8903. Min Range: -5.8903
Max Act: 5.4841. Min Act: -0.1700
Data Index: 1503614 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8903. Min Range: -5.8903
Max Act: 5.4841. Min Act: -0.1700
Data Index: 5647801 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8903. Min Range: -5.8903
Max Act: 5.4216. Min Act: -0.1700
Data Index: 1930394 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8903. Min Range: -5.8903
Max Act: 5.4528. Min Act: -0.1700
Data Index: 2738439 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8903. Min Range: -5.8903
Max Act: 5.4528. Min Act: -0.1700
Data Index: 4276839 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8903. Min Range: -5.8903
Max Act: 5.4528. Min Act: -0.1700
Data Index: 3416869 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8903. Min Range: -5.8903
Max Act: 5.4528. Min Act: -0.1700
Data Index: 4600711 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8903. Min Range: -5.8903
Max Act: 5.4216. Min Act: -0.1700
Data Index: 2858952 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #19