Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1385 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3126. Min Range: -5.3126
Max Act: 5.3126. Min Act: -0.1700
Data Index: 3144265 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3126. Min Range: -5.3126
Max Act: 5.1876. Min Act: -0.1700
Data Index: 8517784 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3126. Min Range: -5.3126
Max Act: 5.1564. Min Act: -0.1700
Data Index: 3813040 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3126. Min Range: -5.3126
Max Act: 5.1251. Min Act: -0.1700
Data Index: 2770727 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3126. Min Range: -5.3126
Max Act: 5.1251. Min Act: -0.1700
Data Index: 1212097 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3126. Min Range: -5.3126
Max Act: 5.0939. Min Act: -0.1700
Data Index: 5731426 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3126. Min Range: -5.3126
Max Act: 5.0939. Min Act: -0.1700
Data Index: 2885463 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3126. Min Range: -5.3126
Max Act: 5.0939. Min Act: -0.1700
Data Index: 2119575 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3126. Min Range: -5.3126
Max Act: 5.0939. Min Act: -0.1700
Data Index: 6828979 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3126. Min Range: -5.3126
Max Act: 5.0939. Min Act: -0.1700
Data Index: 2910676 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3126. Min Range: -5.3126
Max Act: 5.0626. Min Act: -0.1700
Data Index: 7943186 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3126. Min Range: -5.3126
Max Act: 5.0626. Min Act: -0.1700
Data Index: 2910677 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3126. Min Range: -5.3126
Max Act: 5.0001. Min Act: -0.1700
Data Index: 1212098 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3126. Min Range: -5.3126
Max Act: 5.0626. Min Act: -0.1700
Data Index: 3061216 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3126. Min Range: -5.3126
Max Act: 5.0314. Min Act: -0.1700
Data Index: 507616 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3126. Min Range: -5.3126
Max Act: 5.0001. Min Act: -0.1700
Data Index: 1212092 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3126. Min Range: -5.3126
Max Act: 5.0314. Min Act: -0.1700
Data Index: 4750238 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3126. Min Range: -5.3126
Max Act: 5.0001. Min Act: -0.1700
Data Index: 1212094 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3126. Min Range: -5.3126
Max Act: 5.0001. Min Act: -0.1700
Data Index: 1212088 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3126. Min Range: -5.3126
Max Act: 5.0314. Min Act: -0.1700
Data Index: 5658815 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19