Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 722 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9526. Min Range: -3.9526
Max Act: 3.9526. Min Act: -0.1700
Data Index: 4454887 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9526. Min Range: -3.9526
Max Act: 3.9213. Min Act: -0.1700
Data Index: 1210262 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9526. Min Range: -3.9526
Max Act: 3.8900. Min Act: -0.1700
Data Index: 5369480 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9526. Min Range: -3.9526
Max Act: 3.8900. Min Act: -0.1700
Data Index: 804960 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9526. Min Range: -3.9526
Max Act: 3.8275. Min Act: -0.1700
Data Index: 5269851 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9526. Min Range: -3.9526
Max Act: 3.8275. Min Act: -0.1700
Data Index: 3757818 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9526. Min Range: -3.9526
Max Act: 3.7650. Min Act: -0.1700
Data Index: 2251324 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9526. Min Range: -3.9526
Max Act: 3.7337. Min Act: -0.1700
Data Index: 6372901 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9526. Min Range: -3.9526
Max Act: 3.7337. Min Act: -0.1700
Data Index: 8706776 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9526. Min Range: -3.9526
Max Act: 3.7337. Min Act: -0.1700
Data Index: 4016697 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9526. Min Range: -3.9526
Max Act: 3.7180. Min Act: -0.1700
Data Index: 2698775 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9526. Min Range: -3.9526
Max Act: 3.7180. Min Act: -0.1700
Data Index: 5275472 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9526. Min Range: -3.9526
Max Act: 3.7024. Min Act: -0.1700
Data Index: 655634 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9526. Min Range: -3.9526
Max Act: 3.7024. Min Act: -0.1700
Data Index: 802423 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9526. Min Range: -3.9526
Max Act: 3.7024. Min Act: -0.1700
Data Index: 2757732 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9526. Min Range: -3.9526
Max Act: 3.6867. Min Act: -0.1700
Data Index: 4873169 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9526. Min Range: -3.9526
Max Act: 3.6867. Min Act: -0.1700
Data Index: 1590589 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9526. Min Range: -3.9526
Max Act: 3.6711. Min Act: -0.1700
Data Index: 879834 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9526. Min Range: -3.9526
Max Act: 3.6867. Min Act: -0.1700
Data Index: 8468236 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9526. Min Range: -3.9526
Max Act: 3.6867. Min Act: -0.1700
Data Index: 6835225 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19