Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 21 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.9869. Min Act: -0.1700
Data Index: 3552156 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.8931. Min Act: -0.1700
Data Index: 4054017 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.8619. Min Act: -0.1700
Data Index: 8312891 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.8619. Min Act: -0.1700
Data Index: 3088789 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.7681. Min Act: -0.1700
Data Index: 7924044 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.7056. Min Act: -0.1700
Data Index: 7055883 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.7056. Min Act: -0.1700
Data Index: 2088278 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.7056. Min Act: -0.1700
Data Index: 7420602 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.7056. Min Act: -0.1700
Data Index: 4679141 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.6744. Min Act: -0.1700
Data Index: 7201274 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.6431. Min Act: -0.1700
Data Index: 6330985 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.6431. Min Act: -0.1700
Data Index: 3376135 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.6744. Min Act: -0.1700
Data Index: 5506332 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.6431. Min Act: -0.1700
Data Index: 6964323 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.6431. Min Act: -0.1700
Data Index: 8482105 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.6431. Min Act: -0.1700
Data Index: 3654249 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.6119. Min Act: -0.1700
Data Index: 634563 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.6431. Min Act: -0.1700
Data Index: 2914677 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.6119. Min Act: -0.1700
Data Index: 6065303 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.5806. Min Act: -0.1700
Data Index: 4436443 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19