Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3493 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4738. Min Range: -3.4738
Max Act: 3.4738. Min Act: -0.1700
Data Index: 2517833 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4738. Min Range: -3.4738
Max Act: 3.3013. Min Act: -0.1700
Data Index: 5800943 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4738. Min Range: -3.4738
Max Act: 3.3013. Min Act: -0.1700
Data Index: 2992857 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4738. Min Range: -3.4738
Max Act: 3.2699. Min Act: -0.1700
Data Index: 5674333 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4738. Min Range: -3.4738
Max Act: 3.2542. Min Act: -0.1700
Data Index: 839417 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4738. Min Range: -3.4738
Max Act: 3.2384. Min Act: -0.1700
Data Index: 6674569 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4738. Min Range: -3.4738
Max Act: 3.2070. Min Act: -0.1700
Data Index: 1444872 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4738. Min Range: -3.4738
Max Act: 3.1598. Min Act: -0.1700
Data Index: 1883251 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4738. Min Range: -3.4738
Max Act: 3.1756. Min Act: -0.1700
Data Index: 1848822 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4738. Min Range: -3.4738
Max Act: 3.1283. Min Act: -0.1700
Data Index: 5519787 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4738. Min Range: -3.4738
Max Act: 3.1126. Min Act: -0.1700
Data Index: 711657 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4738. Min Range: -3.4738
Max Act: 3.1126. Min Act: -0.1700
Data Index: 5411700 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4738. Min Range: -3.4738
Max Act: 3.0968. Min Act: -0.1700
Data Index: 7372943 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4738. Min Range: -3.4738
Max Act: 3.1126. Min Act: -0.1700
Data Index: 3480376 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4738. Min Range: -3.4738
Max Act: 3.0811. Min Act: -0.1700
Data Index: 5986709 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4738. Min Range: -3.4738
Max Act: 3.0653. Min Act: -0.1700
Data Index: 5342637 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4738. Min Range: -3.4738
Max Act: 3.0653. Min Act: -0.1700
Data Index: 3401695 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4738. Min Range: -3.4738
Max Act: 3.0653. Min Act: -0.1700
Data Index: 5278916 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4738. Min Range: -3.4738
Max Act: 3.0811. Min Act: -0.1700
Data Index: 4588107 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4738. Min Range: -3.4738
Max Act: 3.0653. Min Act: -0.1700
Data Index: 5952 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19