Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4804 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3485. Min Range: -7.3485
Max Act: 7.3485. Min Act: -0.1700
Data Index: 7500032 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3485. Min Range: -7.3485
Max Act: 7.1610. Min Act: -0.1700
Data Index: 2911635 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3485. Min Range: -7.3485
Max Act: 6.9422. Min Act: -0.1700
Data Index: 8465103 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3485. Min Range: -7.3485
Max Act: 6.8797. Min Act: -0.1700
Data Index: 1413297 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3485. Min Range: -7.3485
Max Act: 6.8172. Min Act: -0.1700
Data Index: 1041764 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3485. Min Range: -7.3485
Max Act: 6.7547. Min Act: -0.1700
Data Index: 7398014 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3485. Min Range: -7.3485
Max Act: 6.6922. Min Act: -0.1700
Data Index: 8357241 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3485. Min Range: -7.3485
Max Act: 6.6922. Min Act: -0.1700
Data Index: 7679045 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3485. Min Range: -7.3485
Max Act: 6.5985. Min Act: -0.1700
Data Index: 8633783 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3485. Min Range: -7.3485
Max Act: 6.5672. Min Act: -0.1700
Data Index: 4291395 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3485. Min Range: -7.3485
Max Act: 6.5672. Min Act: -0.1700
Data Index: 7116975 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3485. Min Range: -7.3485
Max Act: 6.5672. Min Act: -0.1700
Data Index: 8257573 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3485. Min Range: -7.3485
Max Act: 6.5360. Min Act: -0.1700
Data Index: 5830480 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3485. Min Range: -7.3485
Max Act: 6.5360. Min Act: -0.1700
Data Index: 2910821 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3485. Min Range: -7.3485
Max Act: 6.5360. Min Act: -0.1700
Data Index: 3030605 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3485. Min Range: -7.3485
Max Act: 6.5047. Min Act: -0.1700
Data Index: 1398054 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3485. Min Range: -7.3485
Max Act: 6.5047. Min Act: -0.1700
Data Index: 243763 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3485. Min Range: -7.3485
Max Act: 6.5360. Min Act: -0.1700
Data Index: 2766097 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3485. Min Range: -7.3485
Max Act: 6.5047. Min Act: -0.1700
Data Index: 6227381 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3485. Min Range: -7.3485
Max Act: 6.4735. Min Act: -0.1700
Data Index: 3975077 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #19