Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3971 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7417. Min Range: -2.7417
Max Act: 2.7417. Min Act: -0.1700
Data Index: 1549141 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7417. Min Range: -2.7417
Max Act: 2.6617. Min Act: -0.1700
Data Index: 7143613 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7417. Min Range: -2.7417
Max Act: 2.6778. Min Act: -0.1700
Data Index: 12791 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7417. Min Range: -2.7417
Max Act: 2.6457. Min Act: -0.1700
Data Index: 1421087 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7417. Min Range: -2.7417
Max Act: 2.6136. Min Act: -0.1700
Data Index: 5986327 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7417. Min Range: -2.7417
Max Act: 2.5975. Min Act: -0.1700
Data Index: 7633625 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7417. Min Range: -2.7417
Max Act: 2.5975. Min Act: -0.1700
Data Index: 5294660 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7417. Min Range: -2.7417
Max Act: 2.5652. Min Act: -0.1700
Data Index: 6740049 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7417. Min Range: -2.7417
Max Act: 2.5652. Min Act: -0.1700
Data Index: 1450407 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7417. Min Range: -2.7417
Max Act: 2.5652. Min Act: -0.1700
Data Index: 5820622 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7417. Min Range: -2.7417
Max Act: 2.5330. Min Act: -0.1700
Data Index: 1052451 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7417. Min Range: -2.7417
Max Act: 2.5491. Min Act: -0.1700
Data Index: 7050697 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7417. Min Range: -2.7417
Max Act: 2.5491. Min Act: -0.1700
Data Index: 248815 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7417. Min Range: -2.7417
Max Act: 2.5330. Min Act: -0.1700
Data Index: 7452893 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7417. Min Range: -2.7417
Max Act: 2.5330. Min Act: -0.1700
Data Index: 7529922 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7417. Min Range: -2.7417
Max Act: 2.5330. Min Act: -0.1700
Data Index: 7144909 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7417. Min Range: -2.7417
Max Act: 2.5330. Min Act: -0.1700
Data Index: 2507022 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7417. Min Range: -2.7417
Max Act: 2.5330. Min Act: -0.1700
Data Index: 6630141 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7417. Min Range: -2.7417
Max Act: 2.5168. Min Act: -0.1700
Data Index: 5249606 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7417. Min Range: -2.7417
Max Act: 2.5168. Min Act: -0.1700
Data Index: 612610 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19