Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1621 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2586. Min Range: -3.2586
Max Act: 3.2586. Min Act: -0.1700
Data Index: 5262533 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2586. Min Range: -3.2586
Max Act: 3.2429. Min Act: -0.1700
Data Index: 3146496 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2586. Min Range: -3.2586
Max Act: 3.2272. Min Act: -0.1700
Data Index: 8167555 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2586. Min Range: -3.2586
Max Act: 3.1328. Min Act: -0.1700
Data Index: 5785572 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2586. Min Range: -3.2586
Max Act: 3.1170. Min Act: -0.1700
Data Index: 711425 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2586. Min Range: -3.2586
Max Act: 3.1485. Min Act: -0.1700
Data Index: 3481815 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2586. Min Range: -3.2586
Max Act: 3.1328. Min Act: -0.1700
Data Index: 3057381 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2586. Min Range: -3.2586
Max Act: 3.1328. Min Act: -0.1700
Data Index: 443085 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2586. Min Range: -3.2586
Max Act: 3.1328. Min Act: -0.1700
Data Index: 8710818 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2586. Min Range: -3.2586
Max Act: 3.1170. Min Act: -0.1700
Data Index: 5478261 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2586. Min Range: -3.2586
Max Act: 3.1170. Min Act: -0.1700
Data Index: 7150256 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2586. Min Range: -3.2586
Max Act: 3.1170. Min Act: -0.1700
Data Index: 2536281 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2586. Min Range: -3.2586
Max Act: 3.0855. Min Act: -0.1700
Data Index: 4134396 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2586. Min Range: -3.2586
Max Act: 3.0855. Min Act: -0.1700
Data Index: 5786687 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2586. Min Range: -3.2586
Max Act: 3.0855. Min Act: -0.1700
Data Index: 3166027 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2586. Min Range: -3.2586
Max Act: 3.1013. Min Act: -0.1700
Data Index: 1563743 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2586. Min Range: -3.2586
Max Act: 3.0855. Min Act: -0.1700
Data Index: 1959148 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2586. Min Range: -3.2586
Max Act: 3.0697. Min Act: -0.1700
Data Index: 6762744 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2586. Min Range: -3.2586
Max Act: 3.0855. Min Act: -0.1700
Data Index: 4957467 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2586. Min Range: -3.2586
Max Act: 3.0540. Min Act: -0.1700
Data Index: 6927046 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19