Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3257 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2891. Min Range: -2.2891
Max Act: 2.2891. Min Act: -0.1700
Data Index: 2153941 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2891. Min Range: -2.2891
Max Act: 2.2726. Min Act: -0.1700
Data Index: 700901 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2891. Min Range: -2.2891
Max Act: 2.2065. Min Act: -0.1700
Data Index: 7089283 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2891. Min Range: -2.2891
Max Act: 2.2230. Min Act: -0.1700
Data Index: 2211490 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2891. Min Range: -2.2891
Max Act: 2.1899. Min Act: -0.1700
Data Index: 1738741 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2891. Min Range: -2.2891
Max Act: 2.1566. Min Act: -0.1700
Data Index: 5812708 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2891. Min Range: -2.2891
Max Act: 2.1566. Min Act: -0.1700
Data Index: 8314670 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2891. Min Range: -2.2891
Max Act: 2.1732. Min Act: -0.1700
Data Index: 3110774 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2891. Min Range: -2.2891
Max Act: 2.1566. Min Act: -0.1700
Data Index: 4514105 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2891. Min Range: -2.2891
Max Act: 2.1732. Min Act: -0.1700
Data Index: 1097534 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2891. Min Range: -2.2891
Max Act: 2.1232. Min Act: -0.1700
Data Index: 1457914 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2891. Min Range: -2.2891
Max Act: 2.1399. Min Act: -0.1700
Data Index: 7562673 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2891. Min Range: -2.2891
Max Act: 2.1232. Min Act: -0.1700
Data Index: 1381437 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2891. Min Range: -2.2891
Max Act: 2.1232. Min Act: -0.1700
Data Index: 1081267 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2891. Min Range: -2.2891
Max Act: 2.1232. Min Act: -0.1700
Data Index: 4493885 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2891. Min Range: -2.2891
Max Act: 2.1232. Min Act: -0.1700
Data Index: 872013 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2891. Min Range: -2.2891
Max Act: 2.1065. Min Act: -0.1700
Data Index: 8313543 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2891. Min Range: -2.2891
Max Act: 2.1065. Min Act: -0.1700
Data Index: 428520 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2891. Min Range: -2.2891
Max Act: 2.0730. Min Act: -0.1700
Data Index: 6882092 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2891. Min Range: -2.2891
Max Act: 2.0898. Min Act: -0.1700
Data Index: 42873 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #19