Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2818 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5907. Min Range: -7.5907
Max Act: 7.5907. Min Act: -0.1700
Data Index: 2041332 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5907. Min Range: -7.5907
Max Act: 7.4969. Min Act: -0.1700
Data Index: 1570364 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5907. Min Range: -7.5907
Max Act: 7.1844. Min Act: -0.1700
Data Index: 5522026 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5907. Min Range: -7.5907
Max Act: 7.2157. Min Act: -0.1700
Data Index: 7224095 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5907. Min Range: -7.5907
Max Act: 7.1219. Min Act: -0.1700
Data Index: 3902850 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5907. Min Range: -7.5907
Max Act: 7.0594. Min Act: -0.1700
Data Index: 8200164 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5907. Min Range: -7.5907
Max Act: 7.0594. Min Act: -0.1700
Data Index: 196454 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5907. Min Range: -7.5907
Max Act: 7.0594. Min Act: -0.1700
Data Index: 6307143 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5907. Min Range: -7.5907
Max Act: 7.0594. Min Act: -0.1700
Data Index: 1613659 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5907. Min Range: -7.5907
Max Act: 7.0282. Min Act: -0.1700
Data Index: 3036684 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5907. Min Range: -7.5907
Max Act: 6.9969. Min Act: -0.1700
Data Index: 6639307 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5907. Min Range: -7.5907
Max Act: 6.9657. Min Act: -0.1700
Data Index: 7567441 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5907. Min Range: -7.5907
Max Act: 6.9344. Min Act: -0.1700
Data Index: 122393 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5907. Min Range: -7.5907
Max Act: 6.9344. Min Act: -0.1700
Data Index: 5812690 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5907. Min Range: -7.5907
Max Act: 6.9657. Min Act: -0.1700
Data Index: 3486709 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5907. Min Range: -7.5907
Max Act: 6.9032. Min Act: -0.1700
Data Index: 5990404 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5907. Min Range: -7.5907
Max Act: 6.9032. Min Act: -0.1700
Data Index: 1602344 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5907. Min Range: -7.5907
Max Act: 6.8719. Min Act: -0.1700
Data Index: 4164088 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5907. Min Range: -7.5907
Max Act: 6.8719. Min Act: -0.1700
Data Index: 7443419 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5907. Min Range: -7.5907
Max Act: 6.8094. Min Act: -0.1700
Data Index: 7623971 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #19