Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3250 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4412. Min Range: -6.4412
Max Act: 6.4412. Min Act: -0.1700
Data Index: 4637889 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4412. Min Range: -6.4412
Max Act: 6.2849. Min Act: -0.1700
Data Index: 3026155 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4412. Min Range: -6.4412
Max Act: 6.2849. Min Act: -0.1700
Data Index: 2812584 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4412. Min Range: -6.4412
Max Act: 6.1912. Min Act: -0.1700
Data Index: 3274027 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4412. Min Range: -6.4412
Max Act: 6.1912. Min Act: -0.1700
Data Index: 6047823 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4412. Min Range: -6.4412
Max Act: 6.1912. Min Act: -0.1700
Data Index: 7856116 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4412. Min Range: -6.4412
Max Act: 6.1599. Min Act: -0.1700
Data Index: 5769356 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4412. Min Range: -6.4412
Max Act: 6.1599. Min Act: -0.1700
Data Index: 1961109 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4412. Min Range: -6.4412
Max Act: 6.1599. Min Act: -0.1700
Data Index: 7653250 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4412. Min Range: -6.4412
Max Act: 6.1287. Min Act: -0.1700
Data Index: 5688632 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4412. Min Range: -6.4412
Max Act: 6.1287. Min Act: -0.1700
Data Index: 3229751 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4412. Min Range: -6.4412
Max Act: 6.0974. Min Act: -0.1700
Data Index: 8092917 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4412. Min Range: -6.4412
Max Act: 6.1287. Min Act: -0.1700
Data Index: 8258103 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4412. Min Range: -6.4412
Max Act: 6.1287. Min Act: -0.1700
Data Index: 8710702 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4412. Min Range: -6.4412
Max Act: 6.1287. Min Act: -0.1700
Data Index: 6806566 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4412. Min Range: -6.4412
Max Act: 6.1287. Min Act: -0.1700
Data Index: 3662449 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4412. Min Range: -6.4412
Max Act: 6.1287. Min Act: -0.1700
Data Index: 6517545 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4412. Min Range: -6.4412
Max Act: 6.0974. Min Act: -0.1700
Data Index: 3865680 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4412. Min Range: -6.4412
Max Act: 6.0974. Min Act: -0.1700
Data Index: 7784892 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4412. Min Range: -6.4412
Max Act: 6.0974. Min Act: -0.1700
Data Index: 4574326 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #19