Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3348 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6440. Min Range: -6.6440
Max Act: 6.6440. Min Act: -0.1700
Data Index: 7810407 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6440. Min Range: -6.6440
Max Act: 5.9252. Min Act: -0.1700
Data Index: 6347773 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6440. Min Range: -6.6440
Max Act: 5.8940. Min Act: -0.1700
Data Index: 6043712 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6440. Min Range: -6.6440
Max Act: 5.8627. Min Act: -0.1700
Data Index: 6636170 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6440. Min Range: -6.6440
Max Act: 5.8627. Min Act: -0.1700
Data Index: 2599262 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6440. Min Range: -6.6440
Max Act: 5.8002. Min Act: -0.1700
Data Index: 6618873 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6440. Min Range: -6.6440
Max Act: 5.7690. Min Act: -0.1700
Data Index: 6861184 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6440. Min Range: -6.6440
Max Act: 5.7690. Min Act: -0.1700
Data Index: 529957 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6440. Min Range: -6.6440
Max Act: 5.7377. Min Act: -0.1700
Data Index: 6465469 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6440. Min Range: -6.6440
Max Act: 5.7065. Min Act: -0.1700
Data Index: 1577183 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6440. Min Range: -6.6440
Max Act: 5.7065. Min Act: -0.1700
Data Index: 6970512 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6440. Min Range: -6.6440
Max Act: 5.7065. Min Act: -0.1700
Data Index: 62915 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6440. Min Range: -6.6440
Max Act: 5.7065. Min Act: -0.1700
Data Index: 3510871 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6440. Min Range: -6.6440
Max Act: 5.7377. Min Act: -0.1700
Data Index: 1675514 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6440. Min Range: -6.6440
Max Act: 5.7065. Min Act: -0.1700
Data Index: 8329909 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6440. Min Range: -6.6440
Max Act: 5.7065. Min Act: -0.1700
Data Index: 2164809 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6440. Min Range: -6.6440
Max Act: 5.6440. Min Act: -0.1700
Data Index: 6811565 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6440. Min Range: -6.6440
Max Act: 5.6440. Min Act: -0.1700
Data Index: 4019994 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6440. Min Range: -6.6440
Max Act: 5.6127. Min Act: -0.1700
Data Index: 8489069 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6440. Min Range: -6.6440
Max Act: 5.5815. Min Act: -0.1700
Data Index: 3035069 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19