Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2052 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4812. Min Range: -4.4812
Max Act: 4.4812. Min Act: -0.1700
Data Index: 2196744 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4812. Min Range: -4.4812
Max Act: 4.2937. Min Act: -0.1698
Data Index: 203265 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4812. Min Range: -4.4812
Max Act: 4.1687. Min Act: -0.1700
Data Index: 2415081 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4812. Min Range: -4.4812
Max Act: 4.1375. Min Act: -0.1700
Data Index: 4038043 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4812. Min Range: -4.4812
Max Act: 4.1062. Min Act: -0.1700
Data Index: 656511 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4812. Min Range: -4.4812
Max Act: 4.0749. Min Act: -0.1700
Data Index: 8078202 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4812. Min Range: -4.4812
Max Act: 4.0749. Min Act: -0.1699
Data Index: 4500691 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4812. Min Range: -4.4812
Max Act: 4.0749. Min Act: -0.1700
Data Index: 2647160 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4812. Min Range: -4.4812
Max Act: 4.0749. Min Act: -0.1700
Data Index: 5586923 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4812. Min Range: -4.4812
Max Act: 4.0437. Min Act: -0.1700
Data Index: 1700760 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4812. Min Range: -4.4812
Max Act: 4.0437. Min Act: -0.1700
Data Index: 8473854 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4812. Min Range: -4.4812
Max Act: 4.0437. Min Act: -0.1700
Data Index: 7588231 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4812. Min Range: -4.4812
Max Act: 4.0124. Min Act: -0.1700
Data Index: 5569492 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4812. Min Range: -4.4812
Max Act: 3.9812. Min Act: -0.1700
Data Index: 891398 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4812. Min Range: -4.4812
Max Act: 4.0124. Min Act: -0.1700
Data Index: 5811894 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4812. Min Range: -4.4812
Max Act: 3.9499. Min Act: -0.1700
Data Index: 5324235 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4812. Min Range: -4.4812
Max Act: 3.9499. Min Act: -0.1700
Data Index: 6229621 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4812. Min Range: -4.4812
Max Act: 3.9499. Min Act: -0.1699
Data Index: 2018968 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4812. Min Range: -4.4812
Max Act: 3.9499. Min Act: -0.1700
Data Index: 1980630 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4812. Min Range: -4.4812
Max Act: 3.9499. Min Act: -0.1700
Data Index: 3202591 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #19