Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1162 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5608. Min Range: -6.5608
Max Act: 6.5608. Min Act: -0.1700
Data Index: 1817709 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5608. Min Range: -6.5608
Max Act: 6.2796. Min Act: -0.1700
Data Index: 4583685 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5608. Min Range: -6.5608
Max Act: 6.3108. Min Act: -0.1700
Data Index: 2408402 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5608. Min Range: -6.5608
Max Act: 6.2483. Min Act: -0.1700
Data Index: 4784263 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5608. Min Range: -6.5608
Max Act: 6.0921. Min Act: -0.1700
Data Index: 8122924 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5608. Min Range: -6.5608
Max Act: 6.0921. Min Act: -0.1700
Data Index: 2406441 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5608. Min Range: -6.5608
Max Act: 5.9983. Min Act: -0.1700
Data Index: 6067910 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5608. Min Range: -6.5608
Max Act: 5.9983. Min Act: -0.1700
Data Index: 241849 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5608. Min Range: -6.5608
Max Act: 5.9983. Min Act: -0.1700
Data Index: 4009358 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5608. Min Range: -6.5608
Max Act: 5.9671. Min Act: -0.1700
Data Index: 4999172 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5608. Min Range: -6.5608
Max Act: 5.9983. Min Act: -0.1700
Data Index: 5121237 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5608. Min Range: -6.5608
Max Act: 5.9671. Min Act: -0.1700
Data Index: 1782571 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5608. Min Range: -6.5608
Max Act: 5.9358. Min Act: -0.1700
Data Index: 7420766 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5608. Min Range: -6.5608
Max Act: 5.9046. Min Act: -0.1700
Data Index: 3959730 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5608. Min Range: -6.5608
Max Act: 5.9358. Min Act: -0.1700
Data Index: 4882823 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5608. Min Range: -6.5608
Max Act: 5.8733. Min Act: -0.1700
Data Index: 2456073 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5608. Min Range: -6.5608
Max Act: 5.9046. Min Act: -0.1700
Data Index: 4245421 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5608. Min Range: -6.5608
Max Act: 5.8733. Min Act: -0.1700
Data Index: 797747 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5608. Min Range: -6.5608
Max Act: 5.8733. Min Act: -0.1700
Data Index: 890590 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5608. Min Range: -6.5608
Max Act: 5.8733. Min Act: -0.1700
Data Index: 4321433 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19