Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5092 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5952. Min Range: -6.5952
Max Act: 6.5952. Min Act: -0.1700
Data Index: 8285225 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5952. Min Range: -6.5952
Max Act: 6.4702. Min Act: -0.1700
Data Index: 3663560 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5952. Min Range: -6.5952
Max Act: 6.5014. Min Act: -0.1700
Data Index: 1744813 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5952. Min Range: -6.5952
Max Act: 6.4702. Min Act: -0.1700
Data Index: 4669215 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5952. Min Range: -6.5952
Max Act: 6.4389. Min Act: -0.1700
Data Index: 2382501 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5952. Min Range: -6.5952
Max Act: 6.4389. Min Act: -0.1700
Data Index: 688488 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5952. Min Range: -6.5952
Max Act: 6.4389. Min Act: -0.1700
Data Index: 7414180 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5952. Min Range: -6.5952
Max Act: 6.4077. Min Act: -0.1700
Data Index: 4734443 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5952. Min Range: -6.5952
Max Act: 6.3764. Min Act: -0.1700
Data Index: 4888427 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5952. Min Range: -6.5952
Max Act: 6.3452. Min Act: -0.1700
Data Index: 5316751 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5952. Min Range: -6.5952
Max Act: 6.3452. Min Act: -0.1700
Data Index: 4706239 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5952. Min Range: -6.5952
Max Act: 6.3452. Min Act: -0.1700
Data Index: 4298786 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5952. Min Range: -6.5952
Max Act: 6.2827. Min Act: -0.1700
Data Index: 835187 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5952. Min Range: -6.5952
Max Act: 6.2202. Min Act: -0.1700
Data Index: 5206726 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5952. Min Range: -6.5952
Max Act: 6.2514. Min Act: -0.1700
Data Index: 3419334 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5952. Min Range: -6.5952
Max Act: 6.2202. Min Act: -0.1700
Data Index: 5651681 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5952. Min Range: -6.5952
Max Act: 6.2202. Min Act: -0.1700
Data Index: 7804447 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5952. Min Range: -6.5952
Max Act: 6.1889. Min Act: -0.1700
Data Index: 51255 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5952. Min Range: -6.5952
Max Act: 6.2202. Min Act: -0.1700
Data Index: 6008578 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5952. Min Range: -6.5952
Max Act: 6.1577. Min Act: -0.1700
Data Index: 6106738 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #19