Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5433 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0840. Min Range: -5.0840
Max Act: 5.0840. Min Act: -0.1700
Data Index: 4017658 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0840. Min Range: -5.0840
Max Act: 5.0215. Min Act: -0.1700
Data Index: 1485001 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0840. Min Range: -5.0840
Max Act: 5.0215. Min Act: -0.1700
Data Index: 741081 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0840. Min Range: -5.0840
Max Act: 4.9902. Min Act: -0.1700
Data Index: 8321918 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0840. Min Range: -5.0840
Max Act: 4.9277. Min Act: -0.1700
Data Index: 1825975 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0840. Min Range: -5.0840
Max Act: 4.9277. Min Act: -0.1700
Data Index: 7680834 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0840. Min Range: -5.0840
Max Act: 4.8340. Min Act: -0.1700
Data Index: 8432445 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0840. Min Range: -5.0840
Max Act: 4.8340. Min Act: -0.1700
Data Index: 8688660 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0840. Min Range: -5.0840
Max Act: 4.8340. Min Act: -0.1700
Data Index: 1107433 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0840. Min Range: -5.0840
Max Act: 4.8027. Min Act: -0.1700
Data Index: 7718308 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0840. Min Range: -5.0840
Max Act: 4.8027. Min Act: -0.1700
Data Index: 3756093 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0840. Min Range: -5.0840
Max Act: 4.8027. Min Act: -0.1700
Data Index: 3115399 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0840. Min Range: -5.0840
Max Act: 4.8027. Min Act: -0.1700
Data Index: 7680858 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0840. Min Range: -5.0840
Max Act: 4.8027. Min Act: -0.1700
Data Index: 7680861 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0840. Min Range: -5.0840
Max Act: 4.8027. Min Act: -0.1700
Data Index: 51496 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0840. Min Range: -5.0840
Max Act: 4.7715. Min Act: -0.1700
Data Index: 2663204 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0840. Min Range: -5.0840
Max Act: 4.7715. Min Act: -0.1700
Data Index: 3863669 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0840. Min Range: -5.0840
Max Act: 4.7402. Min Act: -0.1700
Data Index: 1322465 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0840. Min Range: -5.0840
Max Act: 4.7402. Min Act: -0.1700
Data Index: 7680837 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0840. Min Range: -5.0840
Max Act: 4.7402. Min Act: -0.1700
Data Index: 5463879 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19