Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1563 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3694. Min Range: -7.3694
Max Act: 7.3694. Min Act: -0.1700
Data Index: 4808572 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3694. Min Range: -7.3694
Max Act: 7.3694. Min Act: -0.1700
Data Index: 5711278 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3694. Min Range: -7.3694
Max Act: 7.0569. Min Act: -0.1700
Data Index: 5314248 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3694. Min Range: -7.3694
Max Act: 7.0256. Min Act: -0.1700
Data Index: 2631512 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3694. Min Range: -7.3694
Max Act: 6.9006. Min Act: -0.1700
Data Index: 850553 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3694. Min Range: -7.3694
Max Act: 6.8381. Min Act: -0.1700
Data Index: 2665449 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3694. Min Range: -7.3694
Max Act: 6.8381. Min Act: -0.1700
Data Index: 416428 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3694. Min Range: -7.3694
Max Act: 6.7756. Min Act: -0.1700
Data Index: 2706414 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3694. Min Range: -7.3694
Max Act: 6.7756. Min Act: -0.1700
Data Index: 8726747 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3694. Min Range: -7.3694
Max Act: 6.7131. Min Act: -0.1700
Data Index: 8188795 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3694. Min Range: -7.3694
Max Act: 6.6819. Min Act: -0.1700
Data Index: 7846760 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3694. Min Range: -7.3694
Max Act: 6.6819. Min Act: -0.1700
Data Index: 2847399 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3694. Min Range: -7.3694
Max Act: 6.6194. Min Act: -0.1700
Data Index: 2107088 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3694. Min Range: -7.3694
Max Act: 6.6194. Min Act: -0.1700
Data Index: 3112268 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3694. Min Range: -7.3694
Max Act: 6.5881. Min Act: -0.1700
Data Index: 6696381 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3694. Min Range: -7.3694
Max Act: 6.6194. Min Act: -0.1700
Data Index: 7850005 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3694. Min Range: -7.3694
Max Act: 6.5881. Min Act: -0.1700
Data Index: 4861844 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3694. Min Range: -7.3694
Max Act: 6.5569. Min Act: -0.1700
Data Index: 6730773 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3694. Min Range: -7.3694
Max Act: 6.5256. Min Act: -0.1700
Data Index: 669621 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3694. Min Range: -7.3694
Max Act: 6.4944. Min Act: -0.1700
Data Index: 6969123 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #19