Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4943 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9275. Min Range: -5.9275
Max Act: 5.9275. Min Act: -0.1700
Data Index: 3198409 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9275. Min Range: -5.9275
Max Act: 5.6463. Min Act: -0.1700
Data Index: 7411518 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9275. Min Range: -5.9275
Max Act: 5.5838. Min Act: -0.1700
Data Index: 1693674 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9275. Min Range: -5.9275
Max Act: 5.5213. Min Act: -0.1700
Data Index: 508069 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9275. Min Range: -5.9275
Max Act: 5.4900. Min Act: -0.1700
Data Index: 3775408 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9275. Min Range: -5.9275
Max Act: 5.4275. Min Act: -0.1700
Data Index: 4334975 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9275. Min Range: -5.9275
Max Act: 5.4275. Min Act: -0.1700
Data Index: 8029231 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9275. Min Range: -5.9275
Max Act: 5.4275. Min Act: -0.1700
Data Index: 3775416 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9275. Min Range: -5.9275
Max Act: 5.3963. Min Act: -0.1700
Data Index: 2768162 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9275. Min Range: -5.9275
Max Act: 5.4275. Min Act: -0.1700
Data Index: 3775410 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9275. Min Range: -5.9275
Max Act: 5.3963. Min Act: -0.1700
Data Index: 5029090 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9275. Min Range: -5.9275
Max Act: 5.3650. Min Act: -0.1700
Data Index: 2025194 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9275. Min Range: -5.9275
Max Act: 5.3963. Min Act: -0.1700
Data Index: 383460 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9275. Min Range: -5.9275
Max Act: 5.3338. Min Act: -0.1700
Data Index: 5039729 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9275. Min Range: -5.9275
Max Act: 5.3025. Min Act: -0.1700
Data Index: 1373341 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9275. Min Range: -5.9275
Max Act: 5.3025. Min Act: -0.1700
Data Index: 4677372 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9275. Min Range: -5.9275
Max Act: 5.3025. Min Act: -0.1700
Data Index: 1233715 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9275. Min Range: -5.9275
Max Act: 5.3025. Min Act: -0.1700
Data Index: 7208806 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9275. Min Range: -5.9275
Max Act: 5.2400. Min Act: -0.1700
Data Index: 4981081 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9275. Min Range: -5.9275
Max Act: 5.2400. Min Act: -0.1700
Data Index: 1009860 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19