Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2086 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5803. Min Range: -4.5803
Max Act: 4.5803. Min Act: -0.1700
Data Index: 282087 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5803. Min Range: -4.5803
Max Act: 4.5803. Min Act: -0.1700
Data Index: 424215 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5803. Min Range: -4.5803
Max Act: 4.5803. Min Act: -0.1700
Data Index: 578885 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5803. Min Range: -4.5803
Max Act: 4.5178. Min Act: -0.1700
Data Index: 1030256 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5803. Min Range: -4.5803
Max Act: 4.5178. Min Act: -0.1700
Data Index: 7325884 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5803. Min Range: -4.5803
Max Act: 4.4553. Min Act: -0.1700
Data Index: 8756153 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5803. Min Range: -4.5803
Max Act: 4.3928. Min Act: -0.1700
Data Index: 505905 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5803. Min Range: -4.5803
Max Act: 4.4241. Min Act: -0.1700
Data Index: 6734504 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5803. Min Range: -4.5803
Max Act: 4.3928. Min Act: -0.1700
Data Index: 1638761 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5803. Min Range: -4.5803
Max Act: 4.3928. Min Act: -0.1700
Data Index: 3568973 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5803. Min Range: -4.5803
Max Act: 4.3928. Min Act: -0.1700
Data Index: 3044013 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5803. Min Range: -4.5803
Max Act: 4.3616. Min Act: -0.1700
Data Index: 4521912 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5803. Min Range: -4.5803
Max Act: 4.3616. Min Act: -0.1700
Data Index: 5346300 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5803. Min Range: -4.5803
Max Act: 4.3616. Min Act: -0.1700
Data Index: 6122304 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5803. Min Range: -4.5803
Max Act: 4.3928. Min Act: -0.1700
Data Index: 7922332 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5803. Min Range: -4.5803
Max Act: 4.3616. Min Act: -0.1700
Data Index: 3543536 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5803. Min Range: -4.5803
Max Act: 4.3303. Min Act: -0.1700
Data Index: 3875747 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5803. Min Range: -4.5803
Max Act: 4.3303. Min Act: -0.1700
Data Index: 3379485 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5803. Min Range: -4.5803
Max Act: 4.3303. Min Act: -0.1700
Data Index: 4266954 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5803. Min Range: -4.5803
Max Act: 4.3303. Min Act: -0.1700
Data Index: 2180469 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19