Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4958 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2337. Min Range: -6.2337
Max Act: 6.2337. Min Act: -0.1617
Data Index: 7583639 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2337. Min Range: -6.2337
Max Act: 5.8900. Min Act: -0.1695
Data Index: 1836538 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2337. Min Range: -6.2337
Max Act: 5.7962. Min Act: -0.1647
Data Index: 455000 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2337. Min Range: -6.2337
Max Act: 5.7650. Min Act: -0.1697
Data Index: 3139822 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2337. Min Range: -6.2337
Max Act: 5.7337. Min Act: -0.1700
Data Index: 831417 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2337. Min Range: -6.2337
Max Act: 5.7337. Min Act: -0.1658
Data Index: 44506 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2337. Min Range: -6.2337
Max Act: 5.7025. Min Act: -0.1675
Data Index: 217876 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2337. Min Range: -6.2337
Max Act: 5.6712. Min Act: -0.1695
Data Index: 606742 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2337. Min Range: -6.2337
Max Act: 5.6400. Min Act: -0.1700
Data Index: 605592 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2337. Min Range: -6.2337
Max Act: 5.6712. Min Act: -0.1690
Data Index: 498520 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2337. Min Range: -6.2337
Max Act: 5.6712. Min Act: -0.1700
Data Index: 3798986 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2337. Min Range: -6.2337
Max Act: 5.6087. Min Act: -0.1664
Data Index: 3893187 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2337. Min Range: -6.2337
Max Act: 5.6087. Min Act: -0.1699
Data Index: 286744 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2337. Min Range: -6.2337
Max Act: 5.6087. Min Act: -0.1700
Data Index: 672616 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2337. Min Range: -6.2337
Max Act: 5.6087. Min Act: -0.1700
Data Index: 3027888 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2337. Min Range: -6.2337
Max Act: 5.6087. Min Act: -0.1694
Data Index: 7168965 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2337. Min Range: -6.2337
Max Act: 5.5775. Min Act: -0.1700
Data Index: 7507325 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2337. Min Range: -6.2337
Max Act: 5.5775. Min Act: -0.1667
Data Index: 7283338 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2337. Min Range: -6.2337
Max Act: 5.5462. Min Act: -0.1699
Data Index: 2821485 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2337. Min Range: -6.2337
Max Act: 5.5775. Min Act: -0.1697
Data Index: 7585153 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19