Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 901 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1331. Min Range: -10.1331
Max Act: 10.1331. Min Act: -0.1700
Data Index: 2735975 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1331. Min Range: -10.1331
Max Act: 10.0706. Min Act: -0.1700
Data Index: 5669283 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1331. Min Range: -10.1331
Max Act: 9.5081. Min Act: -0.1700
Data Index: 2179764 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1331. Min Range: -10.1331
Max Act: 9.5706. Min Act: -0.1700
Data Index: 4137102 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1331. Min Range: -10.1331
Max Act: 9.5706. Min Act: -0.1700
Data Index: 2548098 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1331. Min Range: -10.1331
Max Act: 9.5081. Min Act: -0.1700
Data Index: 3084500 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1331. Min Range: -10.1331
Max Act: 9.5081. Min Act: -0.1700
Data Index: 2662479 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1331. Min Range: -10.1331
Max Act: 9.4456. Min Act: -0.1700
Data Index: 6050985 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1331. Min Range: -10.1331
Max Act: 9.5081. Min Act: -0.1700
Data Index: 1096368 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1331. Min Range: -10.1331
Max Act: 9.4456. Min Act: -0.1700
Data Index: 3717549 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1331. Min Range: -10.1331
Max Act: 9.4456. Min Act: -0.1700
Data Index: 2555520 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1331. Min Range: -10.1331
Max Act: 9.3831. Min Act: -0.1700
Data Index: 4888071 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1331. Min Range: -10.1331
Max Act: 9.3831. Min Act: -0.1700
Data Index: 2756259 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1331. Min Range: -10.1331
Max Act: 9.3831. Min Act: -0.1700
Data Index: 5541340 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1331. Min Range: -10.1331
Max Act: 9.3831. Min Act: -0.1700
Data Index: 8693839 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1331. Min Range: -10.1331
Max Act: 9.3831. Min Act: -0.1700
Data Index: 7626377 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1331. Min Range: -10.1331
Max Act: 9.2581. Min Act: -0.1700
Data Index: 3708137 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1331. Min Range: -10.1331
Max Act: 9.3206. Min Act: -0.1699
Data Index: 3657363 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1331. Min Range: -10.1331
Max Act: 9.3206. Min Act: -0.1700
Data Index: 6689 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1331. Min Range: -10.1331
Max Act: 9.3206. Min Act: -0.1700
Data Index: 5826264 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19