Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3638 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4532. Min Range: -5.4532
Max Act: 5.4220. Min Act: -0.1700
Data Index: 5065461 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4532. Min Range: -5.4532
Max Act: 5.4532. Min Act: -0.1700
Data Index: 2287298 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4532. Min Range: -5.4532
Max Act: 5.4220. Min Act: -0.1700
Data Index: 8815682 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4532. Min Range: -5.4532
Max Act: 5.3282. Min Act: -0.1700
Data Index: 5334947 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4532. Min Range: -5.4532
Max Act: 5.3282. Min Act: -0.1700
Data Index: 3979638 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4532. Min Range: -5.4532
Max Act: 5.3282. Min Act: -0.1700
Data Index: 4119070 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4532. Min Range: -5.4532
Max Act: 5.3282. Min Act: -0.1700
Data Index: 5425208 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4532. Min Range: -5.4532
Max Act: 5.2657. Min Act: -0.1700
Data Index: 7089000 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4532. Min Range: -5.4532
Max Act: 5.2032. Min Act: -0.1700
Data Index: 4278982 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4532. Min Range: -5.4532
Max Act: 5.2032. Min Act: -0.1700
Data Index: 5178301 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4532. Min Range: -5.4532
Max Act: 5.2032. Min Act: -0.1700
Data Index: 3001833 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4532. Min Range: -5.4532
Max Act: 5.1720. Min Act: -0.1700
Data Index: 6411739 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4532. Min Range: -5.4532
Max Act: 5.1720. Min Act: -0.1700
Data Index: 1536491 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4532. Min Range: -5.4532
Max Act: 5.1720. Min Act: -0.1700
Data Index: 2851121 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4532. Min Range: -5.4532
Max Act: 5.1720. Min Act: -0.1700
Data Index: 1891866 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4532. Min Range: -5.4532
Max Act: 5.1720. Min Act: -0.1700
Data Index: 8815684 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4532. Min Range: -5.4532
Max Act: 5.1720. Min Act: -0.1700
Data Index: 1416935 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4532. Min Range: -5.4532
Max Act: 5.1720. Min Act: -0.1700
Data Index: 5085744 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4532. Min Range: -5.4532
Max Act: 5.1720. Min Act: -0.1700
Data Index: 6632025 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4532. Min Range: -5.4532
Max Act: 5.1407. Min Act: -0.1700
Data Index: 6602556 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19