Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6328 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5186. Min Range: -6.5186
Max Act: 6.5186. Min Act: -0.1700
Data Index: 5173394 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5186. Min Range: -6.5186
Max Act: 6.4561. Min Act: -0.1700
Data Index: 7151900 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5186. Min Range: -6.5186
Max Act: 6.4561. Min Act: -0.1700
Data Index: 6262670 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5186. Min Range: -6.5186
Max Act: 6.4249. Min Act: -0.1700
Data Index: 4249059 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5186. Min Range: -6.5186
Max Act: 6.4249. Min Act: -0.1700
Data Index: 8245812 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5186. Min Range: -6.5186
Max Act: 6.3936. Min Act: -0.1700
Data Index: 7217352 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5186. Min Range: -6.5186
Max Act: 6.3311. Min Act: -0.1700
Data Index: 1961761 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5186. Min Range: -6.5186
Max Act: 6.2999. Min Act: -0.1700
Data Index: 6180985 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5186. Min Range: -6.5186
Max Act: 6.2686. Min Act: -0.1700
Data Index: 5901838 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5186. Min Range: -6.5186
Max Act: 6.2374. Min Act: -0.1700
Data Index: 2377167 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5186. Min Range: -6.5186
Max Act: 6.2374. Min Act: -0.1700
Data Index: 7919836 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5186. Min Range: -6.5186
Max Act: 6.2374. Min Act: -0.1700
Data Index: 7688963 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5186. Min Range: -6.5186
Max Act: 6.2374. Min Act: -0.1700
Data Index: 8202999 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5186. Min Range: -6.5186
Max Act: 6.2061. Min Act: -0.1700
Data Index: 1704826 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5186. Min Range: -6.5186
Max Act: 6.2061. Min Act: -0.1700
Data Index: 6102589 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5186. Min Range: -6.5186
Max Act: 6.1749. Min Act: -0.1700
Data Index: 1118270 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5186. Min Range: -6.5186
Max Act: 6.1749. Min Act: -0.1700
Data Index: 37117 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5186. Min Range: -6.5186
Max Act: 6.1124. Min Act: -0.1700
Data Index: 8203000 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5186. Min Range: -6.5186
Max Act: 6.1436. Min Act: -0.1700
Data Index: 6523298 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5186. Min Range: -6.5186
Max Act: 6.1749. Min Act: -0.1700
Data Index: 5998492 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19