Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2256 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.5587. Min Range: -9.5587
Max Act: 9.5587. Min Act: -0.1700
Data Index: 6680400 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5587. Min Range: -9.5587
Max Act: 8.6212. Min Act: -0.1700
Data Index: 3210705 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5587. Min Range: -9.5587
Max Act: 8.4962. Min Act: -0.1700
Data Index: 1049219 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5587. Min Range: -9.5587
Max Act: 8.3087. Min Act: -0.1700
Data Index: 3380558 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5587. Min Range: -9.5587
Max Act: 8.3712. Min Act: -0.1700
Data Index: 7122949 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5587. Min Range: -9.5587
Max Act: 8.1837. Min Act: -0.1700
Data Index: 4224885 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5587. Min Range: -9.5587
Max Act: 8.0587. Min Act: -0.1700
Data Index: 5560418 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5587. Min Range: -9.5587
Max Act: 8.3712. Min Act: -0.1700
Data Index: 8641315 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5587. Min Range: -9.5587
Max Act: 7.6837. Min Act: -0.1700
Data Index: 6302050 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5587. Min Range: -9.5587
Max Act: 7.7462. Min Act: -0.1700
Data Index: 2880936 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5587. Min Range: -9.5587
Max Act: 7.9337. Min Act: -0.1700
Data Index: 7120219 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5587. Min Range: -9.5587
Max Act: 6.3712. Min Act: -0.1700
Data Index: 4464629 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5587. Min Range: -9.5587
Max Act: 7.7462. Min Act: -0.1700
Data Index: 548136 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5587. Min Range: -9.5587
Max Act: 7.8712. Min Act: -0.1700
Data Index: 2535868 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5587. Min Range: -9.5587
Max Act: 8.1212. Min Act: -0.1700
Data Index: 8336909 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5587. Min Range: -9.5587
Max Act: 7.6837. Min Act: -0.1700
Data Index: 4500736 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5587. Min Range: -9.5587
Max Act: 7.4025. Min Act: -0.1700
Data Index: 7786117 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5587. Min Range: -9.5587
Max Act: 7.4337. Min Act: -0.1700
Data Index: 474864 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5587. Min Range: -9.5587
Max Act: 7.4337. Min Act: -0.1700
Data Index: 8292935 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5587. Min Range: -9.5587
Max Act: 7.5900. Min Act: -0.1700
Data Index: 1918706 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #19