Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4108 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7901. Min Range: -7.7901
Max Act: 7.7901. Min Act: -0.1700
Data Index: 5737547 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7901. Min Range: -7.7901
Max Act: 7.4776. Min Act: -0.1700
Data Index: 1461618 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7901. Min Range: -7.7901
Max Act: 7.3213. Min Act: -0.1700
Data Index: 6741774 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7901. Min Range: -7.7901
Max Act: 7.2901. Min Act: -0.1700
Data Index: 4205861 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7901. Min Range: -7.7901
Max Act: 7.2276. Min Act: -0.1700
Data Index: 7307882 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7901. Min Range: -7.7901
Max Act: 7.1963. Min Act: -0.1700
Data Index: 1461623 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7901. Min Range: -7.7901
Max Act: 7.1963. Min Act: -0.1700
Data Index: 8421697 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7901. Min Range: -7.7901
Max Act: 7.1651. Min Act: -0.1700
Data Index: 7890054 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7901. Min Range: -7.7901
Max Act: 7.1651. Min Act: -0.1700
Data Index: 3131983 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7901. Min Range: -7.7901
Max Act: 7.1651. Min Act: -0.1700
Data Index: 1278624 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7901. Min Range: -7.7901
Max Act: 7.1338. Min Act: -0.1700
Data Index: 7681741 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7901. Min Range: -7.7901
Max Act: 7.1026. Min Act: -0.1700
Data Index: 8281412 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7901. Min Range: -7.7901
Max Act: 7.1338. Min Act: -0.1700
Data Index: 438753 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7901. Min Range: -7.7901
Max Act: 7.0713. Min Act: -0.1700
Data Index: 6388985 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7901. Min Range: -7.7901
Max Act: 7.0713. Min Act: -0.1700
Data Index: 1987079 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7901. Min Range: -7.7901
Max Act: 7.0713. Min Act: -0.1700
Data Index: 4854488 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7901. Min Range: -7.7901
Max Act: 7.0713. Min Act: -0.1700
Data Index: 542160 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7901. Min Range: -7.7901
Max Act: 7.0401. Min Act: -0.1700
Data Index: 8051378 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7901. Min Range: -7.7901
Max Act: 7.0401. Min Act: -0.1700
Data Index: 5596126 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7901. Min Range: -7.7901
Max Act: 7.0088. Min Act: -0.1700
Data Index: 1394203 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19