Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3885 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1433. Min Range: -8.1433
Max Act: 8.1433. Min Act: -0.1700
Data Index: 1176492 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1433. Min Range: -8.1433
Max Act: 7.9558. Min Act: -0.1700
Data Index: 1777517 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1433. Min Range: -8.1433
Max Act: 7.8933. Min Act: -0.1700
Data Index: 2249085 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1433. Min Range: -8.1433
Max Act: 7.7058. Min Act: -0.1700
Data Index: 2293967 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1433. Min Range: -8.1433
Max Act: 7.7058. Min Act: -0.1700
Data Index: 4425115 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1433. Min Range: -8.1433
Max Act: 7.6433. Min Act: -0.1700
Data Index: 576274 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1433. Min Range: -8.1433
Max Act: 7.5808. Min Act: -0.1700
Data Index: 3713559 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1433. Min Range: -8.1433
Max Act: 7.5183. Min Act: -0.1700
Data Index: 8215196 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1433. Min Range: -8.1433
Max Act: 7.5183. Min Act: -0.1700
Data Index: 3162818 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1433. Min Range: -8.1433
Max Act: 7.4245. Min Act: -0.1700
Data Index: 4784970 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1433. Min Range: -8.1433
Max Act: 7.3620. Min Act: -0.1700
Data Index: 2763135 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1433. Min Range: -8.1433
Max Act: 7.3308. Min Act: -0.1700
Data Index: 4137168 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1433. Min Range: -8.1433
Max Act: 7.3620. Min Act: -0.1700
Data Index: 8754560 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1433. Min Range: -8.1433
Max Act: 7.3308. Min Act: -0.1700
Data Index: 671338 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1433. Min Range: -8.1433
Max Act: 7.2995. Min Act: -0.1700
Data Index: 3385618 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1433. Min Range: -8.1433
Max Act: 7.2995. Min Act: -0.1700
Data Index: 6119220 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1433. Min Range: -8.1433
Max Act: 7.2995. Min Act: -0.1700
Data Index: 7806992 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1433. Min Range: -8.1433
Max Act: 7.2683. Min Act: -0.1700
Data Index: 4693090 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1433. Min Range: -8.1433
Max Act: 7.2683. Min Act: -0.1700
Data Index: 6725379 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1433. Min Range: -8.1433
Max Act: 7.2683. Min Act: -0.1700
Data Index: 8482741 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19