Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 653 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4525. Min Range: -4.4525
Max Act: 4.4525. Min Act: -0.1700
Data Index: 6392342 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4525. Min Range: -4.4525
Max Act: 4.3587. Min Act: -0.1700
Data Index: 6730423 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4525. Min Range: -4.4525
Max Act: 4.3275. Min Act: -0.1700
Data Index: 1101839 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4525. Min Range: -4.4525
Max Act: 4.2337. Min Act: -0.1700
Data Index: 8729830 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4525. Min Range: -4.4525
Max Act: 4.2024. Min Act: -0.1700
Data Index: 2283512 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4525. Min Range: -4.4525
Max Act: 4.2337. Min Act: -0.1700
Data Index: 5013801 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4525. Min Range: -4.4525
Max Act: 4.2024. Min Act: -0.1700
Data Index: 2470472 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4525. Min Range: -4.4525
Max Act: 4.1712. Min Act: -0.1700
Data Index: 3321098 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4525. Min Range: -4.4525
Max Act: 4.2024. Min Act: -0.1700
Data Index: 2231411 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4525. Min Range: -4.4525
Max Act: 4.1712. Min Act: -0.1700
Data Index: 7525899 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4525. Min Range: -4.4525
Max Act: 4.1712. Min Act: -0.1700
Data Index: 5408644 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4525. Min Range: -4.4525
Max Act: 4.1712. Min Act: -0.1700
Data Index: 2291678 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4525. Min Range: -4.4525
Max Act: 4.1712. Min Act: -0.1700
Data Index: 4407742 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4525. Min Range: -4.4525
Max Act: 4.1712. Min Act: -0.1700
Data Index: 1981935 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4525. Min Range: -4.4525
Max Act: 4.1712. Min Act: -0.1700
Data Index: 4129390 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4525. Min Range: -4.4525
Max Act: 4.1712. Min Act: -0.1700
Data Index: 3700365 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4525. Min Range: -4.4525
Max Act: 4.1712. Min Act: -0.1700
Data Index: 4643749 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4525. Min Range: -4.4525
Max Act: 4.1399. Min Act: -0.1700
Data Index: 4504290 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4525. Min Range: -4.4525
Max Act: 4.1399. Min Act: -0.1700
Data Index: 1068691 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4525. Min Range: -4.4525
Max Act: 4.1087. Min Act: -0.1700
Data Index: 4543436 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #19