Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3710 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5589. Min Range: -8.5589
Max Act: 8.5589. Min Act: -0.1700
Data Index: 6582790 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5589. Min Range: -8.5589
Max Act: 8.3089. Min Act: -0.1700
Data Index: 5255219 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5589. Min Range: -8.5589
Max Act: 8.1214. Min Act: -0.1700
Data Index: 3701573 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5589. Min Range: -8.5589
Max Act: 8.0276. Min Act: -0.1700
Data Index: 4082146 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5589. Min Range: -8.5589
Max Act: 7.9339. Min Act: -0.1700
Data Index: 7681286 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5589. Min Range: -8.5589
Max Act: 7.9339. Min Act: -0.1700
Data Index: 605493 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5589. Min Range: -8.5589
Max Act: 7.9026. Min Act: -0.1700
Data Index: 1793726 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5589. Min Range: -8.5589
Max Act: 7.9026. Min Act: -0.1700
Data Index: 5662009 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5589. Min Range: -8.5589
Max Act: 7.9339. Min Act: -0.1700
Data Index: 4244856 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5589. Min Range: -8.5589
Max Act: 7.8714. Min Act: -0.1700
Data Index: 5880556 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5589. Min Range: -8.5589
Max Act: 7.9026. Min Act: -0.1700
Data Index: 8617605 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5589. Min Range: -8.5589
Max Act: 7.7776. Min Act: -0.1700
Data Index: 8233857 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5589. Min Range: -8.5589
Max Act: 7.7776. Min Act: -0.1700
Data Index: 8704402 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5589. Min Range: -8.5589
Max Act: 7.7464. Min Act: -0.1700
Data Index: 8131562 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5589. Min Range: -8.5589
Max Act: 7.7464. Min Act: -0.1700
Data Index: 6376580 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5589. Min Range: -8.5589
Max Act: 7.7464. Min Act: -0.1700
Data Index: 4274369 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5589. Min Range: -8.5589
Max Act: 7.7151. Min Act: -0.1700
Data Index: 1047034 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5589. Min Range: -8.5589
Max Act: 7.6839. Min Act: -0.1700
Data Index: 3868036 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5589. Min Range: -8.5589
Max Act: 7.6839. Min Act: -0.1700
Data Index: 4857376 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5589. Min Range: -8.5589
Max Act: 7.6526. Min Act: -0.1700
Data Index: 4072070 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19