Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3086 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2279. Min Range: -3.2279
Max Act: 3.2279. Min Act: -0.1700
Data Index: 7349432 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2279. Min Range: -3.2279
Max Act: 3.2279. Min Act: -0.1700
Data Index: 7713704 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2279. Min Range: -3.2279
Max Act: 3.2279. Min Act: -0.1700
Data Index: 4728533 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2279. Min Range: -3.2279
Max Act: 3.2279. Min Act: -0.1700
Data Index: 1812777 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2279. Min Range: -3.2279
Max Act: 3.2279. Min Act: -0.1700
Data Index: 1495420 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2279. Min Range: -3.2279
Max Act: 3.2122. Min Act: -0.1700
Data Index: 2124604 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2279. Min Range: -3.2279
Max Act: 3.1965. Min Act: -0.1700
Data Index: 106547 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2279. Min Range: -3.2279
Max Act: 3.1808. Min Act: -0.1700
Data Index: 5217545 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2279. Min Range: -3.2279
Max Act: 3.2122. Min Act: -0.1700
Data Index: 1812778 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2279. Min Range: -3.2279
Max Act: 3.1965. Min Act: -0.1700
Data Index: 4406831 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2279. Min Range: -3.2279
Max Act: 3.1808. Min Act: -0.1700
Data Index: 3369323 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2279. Min Range: -3.2279
Max Act: 3.1965. Min Act: -0.1700
Data Index: 8365348 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2279. Min Range: -3.2279
Max Act: 3.1965. Min Act: -0.1700
Data Index: 7322748 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2279. Min Range: -3.2279
Max Act: 3.1965. Min Act: -0.1700
Data Index: 6866141 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2279. Min Range: -3.2279
Max Act: 3.1808. Min Act: -0.1700
Data Index: 517674 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2279. Min Range: -3.2279
Max Act: 3.1808. Min Act: -0.1700
Data Index: 48968 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2279. Min Range: -3.2279
Max Act: 3.1808. Min Act: -0.1700
Data Index: 1259739 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2279. Min Range: -3.2279
Max Act: 3.1808. Min Act: -0.1700
Data Index: 4548121 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2279. Min Range: -3.2279
Max Act: 3.1808. Min Act: -0.1700
Data Index: 47605 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2279. Min Range: -3.2279
Max Act: 3.1650. Min Act: -0.1700
Data Index: 4206289 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #19