Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 884 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8693. Min Range: -7.8693
Max Act: 7.8693. Min Act: -0.1700
Data Index: 6190053 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8693. Min Range: -7.8693
Max Act: 7.4631. Min Act: -0.1700
Data Index: 4515717 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8693. Min Range: -7.8693
Max Act: 7.2443. Min Act: -0.1700
Data Index: 476565 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8693. Min Range: -7.8693
Max Act: 7.1506. Min Act: -0.1700
Data Index: 2330396 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8693. Min Range: -7.8693
Max Act: 7.0881. Min Act: -0.1700
Data Index: 2417861 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8693. Min Range: -7.8693
Max Act: 7.0568. Min Act: -0.1700
Data Index: 1330052 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8693. Min Range: -7.8693
Max Act: 7.0881. Min Act: -0.1700
Data Index: 719022 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8693. Min Range: -7.8693
Max Act: 6.9943. Min Act: -0.1700
Data Index: 582633 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8693. Min Range: -7.8693
Max Act: 6.8381. Min Act: -0.1700
Data Index: 4200461 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8693. Min Range: -7.8693
Max Act: 6.8068. Min Act: -0.1700
Data Index: 3989466 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8693. Min Range: -7.8693
Max Act: 6.8381. Min Act: -0.1700
Data Index: 6890087 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8693. Min Range: -7.8693
Max Act: 6.8068. Min Act: -0.1700
Data Index: 4101749 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8693. Min Range: -7.8693
Max Act: 6.7756. Min Act: -0.1700
Data Index: 7323982 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8693. Min Range: -7.8693
Max Act: 6.8068. Min Act: -0.1700
Data Index: 8457808 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8693. Min Range: -7.8693
Max Act: 6.7756. Min Act: -0.1700
Data Index: 8380303 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8693. Min Range: -7.8693
Max Act: 6.7756. Min Act: -0.1700
Data Index: 3782559 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8693. Min Range: -7.8693
Max Act: 6.7756. Min Act: -0.1700
Data Index: 7618048 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8693. Min Range: -7.8693
Max Act: 6.7131. Min Act: -0.1700
Data Index: 6490626 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8693. Min Range: -7.8693
Max Act: 6.7443. Min Act: -0.1700
Data Index: 476561 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8693. Min Range: -7.8693
Max Act: 6.6818. Min Act: -0.1700
Data Index: 4384042 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19