Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4092 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.8169. Min Range: -7.8169
Max Act: 7.8169. Min Act: -0.1700
Data Index: 2987886 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8169. Min Range: -7.8169
Max Act: 7.6294. Min Act: -0.1700
Data Index: 445049 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8169. Min Range: -7.8169
Max Act: 7.4106. Min Act: -0.1700
Data Index: 5196407 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8169. Min Range: -7.8169
Max Act: 7.3794. Min Act: -0.1700
Data Index: 5958078 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8169. Min Range: -7.8169
Max Act: 7.2856. Min Act: -0.1700
Data Index: 7932951 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8169. Min Range: -7.8169
Max Act: 7.3481. Min Act: -0.1700
Data Index: 174126 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8169. Min Range: -7.8169
Max Act: 7.2856. Min Act: -0.1700
Data Index: 5073950 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8169. Min Range: -7.8169
Max Act: 7.3169. Min Act: -0.1700
Data Index: 7997725 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8169. Min Range: -7.8169
Max Act: 7.2544. Min Act: -0.1700
Data Index: 173013 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8169. Min Range: -7.8169
Max Act: 7.1919. Min Act: -0.1700
Data Index: 6598323 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8169. Min Range: -7.8169
Max Act: 7.1919. Min Act: -0.1700
Data Index: 7768850 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8169. Min Range: -7.8169
Max Act: 7.1606. Min Act: -0.1700
Data Index: 4560816 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8169. Min Range: -7.8169
Max Act: 7.2231. Min Act: -0.1700
Data Index: 283464 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8169. Min Range: -7.8169
Max Act: 7.1919. Min Act: -0.1700
Data Index: 4560806 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8169. Min Range: -7.8169
Max Act: 7.0981. Min Act: -0.1700
Data Index: 6182296 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8169. Min Range: -7.8169
Max Act: 7.0981. Min Act: -0.1700
Data Index: 4311619 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8169. Min Range: -7.8169
Max Act: 7.1294. Min Act: -0.1700
Data Index: 4517791 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8169. Min Range: -7.8169
Max Act: 7.0981. Min Act: -0.1700
Data Index: 414274 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8169. Min Range: -7.8169
Max Act: 7.0981. Min Act: -0.1700
Data Index: 4675518 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8169. Min Range: -7.8169
Max Act: 7.0669. Min Act: -0.1700
Data Index: 3031036 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19