Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1485 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1762. Min Range: -2.1762
Max Act: 2.1762. Min Act: -0.1700
Data Index: 3401689 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1762. Min Range: -2.1762
Max Act: 2.1762. Min Act: -0.1698
Data Index: 7799512 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1762. Min Range: -2.1762
Max Act: 2.1262. Min Act: -0.1700
Data Index: 3401690 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1762. Min Range: -2.1762
Max Act: 2.1262. Min Act: -0.1700
Data Index: 2814992 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1762. Min Range: -2.1762
Max Act: 2.1095. Min Act: -0.1700
Data Index: 1723893 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1762. Min Range: -2.1762
Max Act: 2.0928. Min Act: -0.1698
Data Index: 5304782 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1762. Min Range: -2.1762
Max Act: 2.0928. Min Act: -0.1700
Data Index: 707307 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1762. Min Range: -2.1762
Max Act: 2.1095. Min Act: -0.1700
Data Index: 4304079 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1762. Min Range: -2.1762
Max Act: 2.0928. Min Act: -0.1697
Data Index: 1123184 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1762. Min Range: -2.1762
Max Act: 2.0592. Min Act: -0.1700
Data Index: 2242110 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1762. Min Range: -2.1762
Max Act: 2.0760. Min Act: -0.1700
Data Index: 4513581 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1762. Min Range: -2.1762
Max Act: 2.0760. Min Act: -0.1700
Data Index: 2350550 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1762. Min Range: -2.1762
Max Act: 2.0928. Min Act: -0.1698
Data Index: 797446 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1762. Min Range: -2.1762
Max Act: 2.0760. Min Act: -0.1700
Data Index: 1425431 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1762. Min Range: -2.1762
Max Act: 2.0760. Min Act: -0.1700
Data Index: 5928710 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1762. Min Range: -2.1762
Max Act: 2.0760. Min Act: -0.1700
Data Index: 4467574 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1762. Min Range: -2.1762
Max Act: 2.0760. Min Act: -0.1697
Data Index: 6251221 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1762. Min Range: -2.1762
Max Act: 2.0760. Min Act: -0.1700
Data Index: 4607543 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1762. Min Range: -2.1762
Max Act: 2.0592. Min Act: -0.1700
Data Index: 5663963 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1762. Min Range: -2.1762
Max Act: 2.0760. Min Act: -0.1700
Data Index: 8524466 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19