Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3026 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3213. Min Range: -7.3213
Max Act: 7.3213. Min Act: -0.1700
Data Index: 4262917 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3213. Min Range: -7.3213
Max Act: 7.0088. Min Act: -0.1700
Data Index: 6507579 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3213. Min Range: -7.3213
Max Act: 6.8525. Min Act: -0.1700
Data Index: 8651123 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3213. Min Range: -7.3213
Max Act: 6.8213. Min Act: -0.1700
Data Index: 1462780 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3213. Min Range: -7.3213
Max Act: 6.7588. Min Act: -0.1700
Data Index: 762911 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3213. Min Range: -7.3213
Max Act: 6.7275. Min Act: -0.1700
Data Index: 6952195 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3213. Min Range: -7.3213
Max Act: 6.5088. Min Act: -0.1700
Data Index: 4362126 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3213. Min Range: -7.3213
Max Act: 6.4775. Min Act: -0.1700
Data Index: 5584664 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3213. Min Range: -7.3213
Max Act: 6.4463. Min Act: -0.1700
Data Index: 6357958 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3213. Min Range: -7.3213
Max Act: 6.4775. Min Act: -0.1700
Data Index: 6324003 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3213. Min Range: -7.3213
Max Act: 6.3525. Min Act: -0.1700
Data Index: 2772936 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3213. Min Range: -7.3213
Max Act: 6.3838. Min Act: -0.1700
Data Index: 2087684 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3213. Min Range: -7.3213
Max Act: 6.3525. Min Act: -0.1700
Data Index: 7405547 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3213. Min Range: -7.3213
Max Act: 6.3838. Min Act: -0.1700
Data Index: 1170216 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3213. Min Range: -7.3213
Max Act: 6.3213. Min Act: -0.1700
Data Index: 4196950 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3213. Min Range: -7.3213
Max Act: 6.2900. Min Act: -0.1700
Data Index: 2695073 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3213. Min Range: -7.3213
Max Act: 6.2900. Min Act: -0.1700
Data Index: 2589781 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3213. Min Range: -7.3213
Max Act: 6.3213. Min Act: -0.1700
Data Index: 5247368 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3213. Min Range: -7.3213
Max Act: 6.2588. Min Act: -0.1700
Data Index: 45356 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3213. Min Range: -7.3213
Max Act: 6.2588. Min Act: -0.1700
Data Index: 4548485 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #19