Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1793 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9707. Min Range: -4.9707
Max Act: 4.9707. Min Act: -0.1700
Data Index: 4417061 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9707. Min Range: -4.9707
Max Act: 4.9395. Min Act: -0.1700
Data Index: 185971 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9707. Min Range: -4.9707
Max Act: 4.9395. Min Act: -0.1700
Data Index: 380045 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9707. Min Range: -4.9707
Max Act: 4.8457. Min Act: -0.1700
Data Index: 6833286 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9707. Min Range: -4.9707
Max Act: 4.8145. Min Act: -0.1700
Data Index: 1454196 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9707. Min Range: -4.9707
Max Act: 4.8457. Min Act: -0.1700
Data Index: 466454 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9707. Min Range: -4.9707
Max Act: 4.8145. Min Act: -0.1700
Data Index: 1468924 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9707. Min Range: -4.9707
Max Act: 4.7832. Min Act: -0.1700
Data Index: 8668629 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9707. Min Range: -4.9707
Max Act: 4.7520. Min Act: -0.1700
Data Index: 6990764 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9707. Min Range: -4.9707
Max Act: 4.7207. Min Act: -0.1700
Data Index: 8511503 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9707. Min Range: -4.9707
Max Act: 4.7207. Min Act: -0.1700
Data Index: 1127600 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9707. Min Range: -4.9707
Max Act: 4.7520. Min Act: -0.1700
Data Index: 6241119 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9707. Min Range: -4.9707
Max Act: 4.6895. Min Act: -0.1700
Data Index: 948799 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9707. Min Range: -4.9707
Max Act: 4.6895. Min Act: -0.1700
Data Index: 6762886 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9707. Min Range: -4.9707
Max Act: 4.6895. Min Act: -0.1700
Data Index: 4882232 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9707. Min Range: -4.9707
Max Act: 4.6582. Min Act: -0.1700
Data Index: 1191702 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9707. Min Range: -4.9707
Max Act: 4.6895. Min Act: -0.1700
Data Index: 481028 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9707. Min Range: -4.9707
Max Act: 4.6270. Min Act: -0.1700
Data Index: 7408466 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9707. Min Range: -4.9707
Max Act: 4.6270. Min Act: -0.1700
Data Index: 1808471 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9707. Min Range: -4.9707
Max Act: 4.6270. Min Act: -0.1700
Data Index: 6462375 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19