Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 999 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.3407. Min Act: -0.1700
Data Index: 1171643 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.3095. Min Act: -0.1700
Data Index: 7412742 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.3407. Min Act: -0.1700
Data Index: 7682662 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.2782. Min Act: -0.1700
Data Index: 4441155 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.2782. Min Act: -0.1700
Data Index: 7792625 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.2782. Min Act: -0.1700
Data Index: 5197557 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.2470. Min Act: -0.1700
Data Index: 4521431 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.2470. Min Act: -0.1700
Data Index: 2181475 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.2782. Min Act: -0.1700
Data Index: 7799781 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.2157. Min Act: -0.1700
Data Index: 4783624 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.2157. Min Act: -0.1700
Data Index: 6124884 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.1532. Min Act: -0.1700
Data Index: 7477230 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.1845. Min Act: -0.1700
Data Index: 1150483 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.1845. Min Act: -0.1700
Data Index: 4088729 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.1845. Min Act: -0.1700
Data Index: 3866778 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.1845. Min Act: -0.1700
Data Index: 5128967 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.1845. Min Act: -0.1700
Data Index: 5716695 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.1845. Min Act: -0.1700
Data Index: 3835671 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.1845. Min Act: -0.1700
Data Index: 5547955 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.1845. Min Act: -0.1700
Data Index: 8703307 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #19