Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4690 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2329. Min Range: -4.2329
Max Act: 4.2329. Min Act: -0.1700
Data Index: 4149720 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2329. Min Range: -4.2329
Max Act: 4.2329. Min Act: -0.1700
Data Index: 3930355 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2329. Min Range: -4.2329
Max Act: 4.1392. Min Act: -0.1700
Data Index: 2595089 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2329. Min Range: -4.2329
Max Act: 4.1392. Min Act: -0.1700
Data Index: 3882701 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2329. Min Range: -4.2329
Max Act: 4.0767. Min Act: -0.1700
Data Index: 5925211 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2329. Min Range: -4.2329
Max Act: 4.0141. Min Act: -0.1700
Data Index: 4826259 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2329. Min Range: -4.2329
Max Act: 3.9516. Min Act: -0.1700
Data Index: 7361152 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2329. Min Range: -4.2329
Max Act: 3.9829. Min Act: -0.1700
Data Index: 1796634 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2329. Min Range: -4.2329
Max Act: 3.9516. Min Act: -0.1700
Data Index: 3574606 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2329. Min Range: -4.2329
Max Act: 3.9516. Min Act: -0.1700
Data Index: 7946846 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2329. Min Range: -4.2329
Max Act: 3.9204. Min Act: -0.1700
Data Index: 858804 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2329. Min Range: -4.2329
Max Act: 3.8578. Min Act: -0.1700
Data Index: 1827150 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2329. Min Range: -4.2329
Max Act: 3.8578. Min Act: -0.1700
Data Index: 4676340 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2329. Min Range: -4.2329
Max Act: 3.8266. Min Act: -0.1700
Data Index: 7491557 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2329. Min Range: -4.2329
Max Act: 3.7640. Min Act: -0.1700
Data Index: 5265869 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2329. Min Range: -4.2329
Max Act: 3.7640. Min Act: -0.1700
Data Index: 3711447 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2329. Min Range: -4.2329
Max Act: 3.7640. Min Act: -0.1700
Data Index: 3865691 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2329. Min Range: -4.2329
Max Act: 3.7640. Min Act: -0.1700
Data Index: 4999840 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2329. Min Range: -4.2329
Max Act: 3.7953. Min Act: -0.1700
Data Index: 6733425 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2329. Min Range: -4.2329
Max Act: 3.7953. Min Act: -0.1700
Data Index: 1827149 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19