Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3568 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1693. Min Range: -8.1693
Max Act: 8.1693. Min Act: -0.1700
Data Index: 1786069 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1693. Min Range: -8.1693
Max Act: 7.8568. Min Act: -0.1700
Data Index: 3610941 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1693. Min Range: -8.1693
Max Act: 7.3881. Min Act: -0.1700
Data Index: 3959568 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1693. Min Range: -8.1693
Max Act: 7.2318. Min Act: -0.1700
Data Index: 7069173 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1693. Min Range: -8.1693
Max Act: 7.1693. Min Act: -0.1700
Data Index: 4242988 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1693. Min Range: -8.1693
Max Act: 7.1693. Min Act: -0.1700
Data Index: 7722716 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1693. Min Range: -8.1693
Max Act: 7.0443. Min Act: -0.1700
Data Index: 7483885 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1693. Min Range: -8.1693
Max Act: 7.0443. Min Act: -0.1700
Data Index: 7672075 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1693. Min Range: -8.1693
Max Act: 7.0131. Min Act: -0.1700
Data Index: 6363017 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1693. Min Range: -8.1693
Max Act: 6.9506. Min Act: -0.1700
Data Index: 5967479 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1693. Min Range: -8.1693
Max Act: 6.9193. Min Act: -0.1700
Data Index: 6998578 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1693. Min Range: -8.1693
Max Act: 6.9193. Min Act: -0.1700
Data Index: 6445207 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1693. Min Range: -8.1693
Max Act: 6.9193. Min Act: -0.1700
Data Index: 8410457 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1693. Min Range: -8.1693
Max Act: 6.8881. Min Act: -0.1700
Data Index: 5267143 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1693. Min Range: -8.1693
Max Act: 6.8881. Min Act: -0.1700
Data Index: 3983636 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1693. Min Range: -8.1693
Max Act: 6.8881. Min Act: -0.1700
Data Index: 4624353 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1693. Min Range: -8.1693
Max Act: 6.8881. Min Act: -0.1700
Data Index: 8439626 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1693. Min Range: -8.1693
Max Act: 6.8568. Min Act: -0.1700
Data Index: 2176684 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1693. Min Range: -8.1693
Max Act: 6.8256. Min Act: -0.1700
Data Index: 7768988 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1693. Min Range: -8.1693
Max Act: 6.8256. Min Act: -0.1700
Data Index: 3611233 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19