Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3430 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2345. Min Range: -7.2345
Max Act: 7.2345. Min Act: -0.1700
Data Index: 4869397 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2345. Min Range: -7.2345
Max Act: 7.1407. Min Act: -0.1700
Data Index: 3849767 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2345. Min Range: -7.2345
Max Act: 7.1095. Min Act: -0.1700
Data Index: 8489065 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2345. Min Range: -7.2345
Max Act: 7.0470. Min Act: -0.1700
Data Index: 3421523 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2345. Min Range: -7.2345
Max Act: 7.0470. Min Act: -0.1700
Data Index: 7261228 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2345. Min Range: -7.2345
Max Act: 7.0157. Min Act: -0.1700
Data Index: 43163 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2345. Min Range: -7.2345
Max Act: 6.9845. Min Act: -0.1700
Data Index: 4154307 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2345. Min Range: -7.2345
Max Act: 6.9220. Min Act: -0.1700
Data Index: 1231603 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2345. Min Range: -7.2345
Max Act: 6.9220. Min Act: -0.1700
Data Index: 8499805 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2345. Min Range: -7.2345
Max Act: 6.8907. Min Act: -0.1700
Data Index: 3697537 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2345. Min Range: -7.2345
Max Act: 6.8595. Min Act: -0.1700
Data Index: 2972213 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2345. Min Range: -7.2345
Max Act: 6.8595. Min Act: -0.1700
Data Index: 2914439 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2345. Min Range: -7.2345
Max Act: 6.8907. Min Act: -0.1700
Data Index: 8018259 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2345. Min Range: -7.2345
Max Act: 6.8282. Min Act: -0.1700
Data Index: 4374326 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2345. Min Range: -7.2345
Max Act: 6.8282. Min Act: -0.1700
Data Index: 6464136 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2345. Min Range: -7.2345
Max Act: 6.8282. Min Act: -0.1700
Data Index: 8175653 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2345. Min Range: -7.2345
Max Act: 6.7970. Min Act: -0.1700
Data Index: 5019810 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2345. Min Range: -7.2345
Max Act: 6.7970. Min Act: -0.1700
Data Index: 1600258 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2345. Min Range: -7.2345
Max Act: 6.7970. Min Act: -0.1700
Data Index: 8579785 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2345. Min Range: -7.2345
Max Act: 6.7970. Min Act: -0.1700
Data Index: 7267651 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19