Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2570 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7698. Min Range: -6.7698
Max Act: 6.7698. Min Act: -0.1700
Data Index: 4196294 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7698. Min Range: -6.7698
Max Act: 6.4261. Min Act: -0.1700
Data Index: 2991653 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7698. Min Range: -6.7698
Max Act: 6.3323. Min Act: -0.1700
Data Index: 6737125 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7698. Min Range: -6.7698
Max Act: 6.3011. Min Act: -0.1700
Data Index: 4933425 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7698. Min Range: -6.7698
Max Act: 6.3011. Min Act: -0.1700
Data Index: 2849584 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7698. Min Range: -6.7698
Max Act: 6.1761. Min Act: -0.1700
Data Index: 4618474 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7698. Min Range: -6.7698
Max Act: 6.1761. Min Act: -0.1700
Data Index: 3154994 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7698. Min Range: -6.7698
Max Act: 6.1761. Min Act: -0.1700
Data Index: 8562894 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7698. Min Range: -6.7698
Max Act: 6.1761. Min Act: -0.1700
Data Index: 8359153 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7698. Min Range: -6.7698
Max Act: 6.1761. Min Act: -0.1700
Data Index: 2059451 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7698. Min Range: -6.7698
Max Act: 6.1761. Min Act: -0.1700
Data Index: 602125 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7698. Min Range: -6.7698
Max Act: 6.1761. Min Act: -0.1700
Data Index: 6953537 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7698. Min Range: -6.7698
Max Act: 6.1761. Min Act: -0.1700
Data Index: 4000072 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7698. Min Range: -6.7698
Max Act: 6.1761. Min Act: -0.1700
Data Index: 3056193 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7698. Min Range: -6.7698
Max Act: 6.1761. Min Act: -0.1700
Data Index: 7390791 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7698. Min Range: -6.7698
Max Act: 6.1761. Min Act: -0.1700
Data Index: 3966930 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7698. Min Range: -6.7698
Max Act: 6.1448. Min Act: -0.1700
Data Index: 1203548 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7698. Min Range: -6.7698
Max Act: 6.1136. Min Act: -0.1700
Data Index: 3559905 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7698. Min Range: -6.7698
Max Act: 6.0511. Min Act: -0.1700
Data Index: 331092 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7698. Min Range: -6.7698
Max Act: 6.0511. Min Act: -0.1700
Data Index: 6834542 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19