Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1541 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8969. Min Range: -4.8969
Max Act: 4.8969. Min Act: -0.1700
Data Index: 792878 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8969. Min Range: -4.8969
Max Act: 4.7719. Min Act: -0.1700
Data Index: 308138 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8969. Min Range: -4.8969
Max Act: 4.7094. Min Act: -0.1700
Data Index: 8184919 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8969. Min Range: -4.8969
Max Act: 4.6781. Min Act: -0.1700
Data Index: 8406918 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8969. Min Range: -4.8969
Max Act: 4.5844. Min Act: -0.1700
Data Index: 2978010 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8969. Min Range: -4.8969
Max Act: 4.6469. Min Act: -0.1700
Data Index: 8413495 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8969. Min Range: -4.8969
Max Act: 4.5844. Min Act: -0.1700
Data Index: 4142983 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8969. Min Range: -4.8969
Max Act: 4.5844. Min Act: -0.1700
Data Index: 3201793 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8969. Min Range: -4.8969
Max Act: 4.5531. Min Act: -0.1700
Data Index: 630083 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8969. Min Range: -4.8969
Max Act: 4.5531. Min Act: -0.1700
Data Index: 4368443 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8969. Min Range: -4.8969
Max Act: 4.5531. Min Act: -0.1700
Data Index: 6527013 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8969. Min Range: -4.8969
Max Act: 4.5531. Min Act: -0.1700
Data Index: 4748387 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8969. Min Range: -4.8969
Max Act: 4.5531. Min Act: -0.1700
Data Index: 2473958 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8969. Min Range: -4.8969
Max Act: 4.5219. Min Act: -0.1700
Data Index: 8759951 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8969. Min Range: -4.8969
Max Act: 4.5219. Min Act: -0.1700
Data Index: 5712483 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8969. Min Range: -4.8969
Max Act: 4.4906. Min Act: -0.1700
Data Index: 5781162 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8969. Min Range: -4.8969
Max Act: 4.5531. Min Act: -0.1700
Data Index: 4971536 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8969. Min Range: -4.8969
Max Act: 4.5531. Min Act: -0.1700
Data Index: 379650 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8969. Min Range: -4.8969
Max Act: 4.4906. Min Act: -0.1700
Data Index: 4229193 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8969. Min Range: -4.8969
Max Act: 4.5219. Min Act: -0.1700
Data Index: 2903896 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19