Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 576 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2571. Min Range: -8.2571
Max Act: 8.2571. Min Act: -0.1700
Data Index: 5999936 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2571. Min Range: -8.2571
Max Act: 8.1321. Min Act: -0.1700
Data Index: 7667087 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2571. Min Range: -8.2571
Max Act: 8.0071. Min Act: -0.1700
Data Index: 4594676 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2571. Min Range: -8.2571
Max Act: 8.0071. Min Act: -0.1700
Data Index: 5209154 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2571. Min Range: -8.2571
Max Act: 8.0071. Min Act: -0.1700
Data Index: 3077402 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2571. Min Range: -8.2571
Max Act: 8.0071. Min Act: -0.1700
Data Index: 5345467 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2571. Min Range: -8.2571
Max Act: 8.0071. Min Act: 0.0198
Data Index: 8515556 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2571. Min Range: -8.2571
Max Act: 7.9446. Min Act: -0.1700
Data Index: 6706839 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2571. Min Range: -8.2571
Max Act: 7.9446. Min Act: -0.1700
Data Index: 8027332 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2571. Min Range: -8.2571
Max Act: 7.9446. Min Act: -0.1700
Data Index: 73921 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2571. Min Range: -8.2571
Max Act: 7.8821. Min Act: -0.1700
Data Index: 3894781 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2571. Min Range: -8.2571
Max Act: 7.8821. Min Act: -0.1700
Data Index: 1481043 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2571. Min Range: -8.2571
Max Act: 7.8821. Min Act: -0.1700
Data Index: 5672557 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2571. Min Range: -8.2571
Max Act: 7.8821. Min Act: -0.1700
Data Index: 3098541 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2571. Min Range: -8.2571
Max Act: 7.8821. Min Act: -0.1700
Data Index: 933754 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2571. Min Range: -8.2571
Max Act: 7.8821. Min Act: -0.1700
Data Index: 7180028 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2571. Min Range: -8.2571
Max Act: 7.8821. Min Act: -0.1700
Data Index: 1684567 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2571. Min Range: -8.2571
Max Act: 7.8196. Min Act: -0.1700
Data Index: 6422068 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2571. Min Range: -8.2571
Max Act: 7.8821. Min Act: -0.1700
Data Index: 6422069 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2571. Min Range: -8.2571
Max Act: 7.8196. Min Act: -0.1648
Data Index: 3130763 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #19