Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2511 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.9767. Min Range: -9.9767
Max Act: 9.9767. Min Act: -0.1700
Data Index: 3116299 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9767. Min Range: -9.9767
Max Act: 9.6017. Min Act: -0.1700
Data Index: 3521349 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9767. Min Range: -9.9767
Max Act: 9.4767. Min Act: -0.1694
Data Index: 895238 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9767. Min Range: -9.9767
Max Act: 9.2892. Min Act: -0.1700
Data Index: 5216893 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9767. Min Range: -9.9767
Max Act: 9.2892. Min Act: -0.1696
Data Index: 3038601 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9767. Min Range: -9.9767
Max Act: 9.1642. Min Act: -0.1687
Data Index: 2888020 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9767. Min Range: -9.9767
Max Act: 9.1642. Min Act: -0.1700
Data Index: 8445487 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9767. Min Range: -9.9767
Max Act: 9.1017. Min Act: -0.1700
Data Index: 7595888 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9767. Min Range: -9.9767
Max Act: 9.1017. Min Act: -0.1699
Data Index: 2019017 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9767. Min Range: -9.9767
Max Act: 9.0392. Min Act: -0.1684
Data Index: 8215574 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9767. Min Range: -9.9767
Max Act: 9.1017. Min Act: -0.1698
Data Index: 2019016 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9767. Min Range: -9.9767
Max Act: 9.0392. Min Act: -0.1696
Data Index: 6274462 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9767. Min Range: -9.9767
Max Act: 9.0392. Min Act: -0.1690
Data Index: 7031600 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9767. Min Range: -9.9767
Max Act: 9.0392. Min Act: -0.1700
Data Index: 1133637 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9767. Min Range: -9.9767
Max Act: 8.9767. Min Act: -0.1700
Data Index: 4008066 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9767. Min Range: -9.9767
Max Act: 9.0392. Min Act: -0.1700
Data Index: 8122968 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9767. Min Range: -9.9767
Max Act: 9.0392. Min Act: -0.1700
Data Index: 8351900 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9767. Min Range: -9.9767
Max Act: 9.0392. Min Act: -0.1690
Data Index: 6256782 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9767. Min Range: -9.9767
Max Act: 8.9767. Min Act: -0.1700
Data Index: 902459 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9767. Min Range: -9.9767
Max Act: 8.9767. Min Act: -0.1700
Data Index: 4263364 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19