Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1503 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0176. Min Range: -3.0176
Max Act: 3.0176. Min Act: -0.1700
Data Index: 2649445 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0176. Min Range: -3.0176
Max Act: 3.0018. Min Act: -0.1700
Data Index: 730316 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0176. Min Range: -3.0176
Max Act: 2.8910. Min Act: -0.1700
Data Index: 6037954 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0176. Min Range: -3.0176
Max Act: 2.9069. Min Act: -0.1700
Data Index: 3762478 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0176. Min Range: -3.0176
Max Act: 2.9069. Min Act: -0.1700
Data Index: 3792755 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0176. Min Range: -3.0176
Max Act: 2.8910. Min Act: -0.1700
Data Index: 4492375 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0176. Min Range: -3.0176
Max Act: 2.8910. Min Act: -0.1700
Data Index: 1503010 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0176. Min Range: -3.0176
Max Act: 2.8751. Min Act: -0.1700
Data Index: 5968660 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0176. Min Range: -3.0176
Max Act: 2.8593. Min Act: -0.1700
Data Index: 2666464 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0176. Min Range: -3.0176
Max Act: 2.8434. Min Act: -0.1700
Data Index: 6292377 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0176. Min Range: -3.0176
Max Act: 2.8434. Min Act: -0.1700
Data Index: 8521953 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0176. Min Range: -3.0176
Max Act: 2.8434. Min Act: -0.1700
Data Index: 2649444 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0176. Min Range: -3.0176
Max Act: 2.8434. Min Act: -0.1700
Data Index: 4492367 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0176. Min Range: -3.0176
Max Act: 2.8434. Min Act: -0.1700
Data Index: 3646444 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0176. Min Range: -3.0176
Max Act: 2.8434. Min Act: -0.1700
Data Index: 2091240 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0176. Min Range: -3.0176
Max Act: 2.8434. Min Act: -0.1700
Data Index: 113680 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0176. Min Range: -3.0176
Max Act: 2.8275. Min Act: -0.1700
Data Index: 1935315 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0176. Min Range: -3.0176
Max Act: 2.8275. Min Act: -0.1700
Data Index: 4492368 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0176. Min Range: -3.0176
Max Act: 2.8116. Min Act: -0.1700
Data Index: 6037949 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0176. Min Range: -3.0176
Max Act: 2.8116. Min Act: -0.1700
Data Index: 2666472 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19