Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4872 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2731. Min Range: -7.2731
Max Act: 7.2731. Min Act: -0.1700
Data Index: 682187 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2731. Min Range: -7.2731
Max Act: 6.7419. Min Act: -0.1700
Data Index: 5650136 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2731. Min Range: -7.2731
Max Act: 6.5856. Min Act: -0.1700
Data Index: 8744301 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2731. Min Range: -7.2731
Max Act: 6.3981. Min Act: -0.1700
Data Index: 1878849 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2731. Min Range: -7.2731
Max Act: 6.3669. Min Act: -0.1700
Data Index: 4640817 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2731. Min Range: -7.2731
Max Act: 6.2731. Min Act: -0.1700
Data Index: 105055 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2731. Min Range: -7.2731
Max Act: 6.2419. Min Act: -0.1700
Data Index: 8542168 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2731. Min Range: -7.2731
Max Act: 6.2106. Min Act: -0.1700
Data Index: 6255069 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2731. Min Range: -7.2731
Max Act: 6.1794. Min Act: -0.1700
Data Index: 5323704 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2731. Min Range: -7.2731
Max Act: 6.1481. Min Act: -0.1700
Data Index: 3611465 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2731. Min Range: -7.2731
Max Act: 6.1169. Min Act: -0.1700
Data Index: 1263323 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2731. Min Range: -7.2731
Max Act: 6.0856. Min Act: -0.1700
Data Index: 3347831 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2731. Min Range: -7.2731
Max Act: 6.0856. Min Act: -0.1700
Data Index: 7957077 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2731. Min Range: -7.2731
Max Act: 5.9919. Min Act: -0.1700
Data Index: 7269917 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2731. Min Range: -7.2731
Max Act: 6.0231. Min Act: -0.1700
Data Index: 3110521 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2731. Min Range: -7.2731
Max Act: 5.9919. Min Act: -0.1700
Data Index: 6857012 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2731. Min Range: -7.2731
Max Act: 5.9919. Min Act: -0.1700
Data Index: 7204464 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2731. Min Range: -7.2731
Max Act: 5.9919. Min Act: -0.1700
Data Index: 5953321 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2731. Min Range: -7.2731
Max Act: 5.9919. Min Act: -0.1700
Data Index: 1890453 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2731. Min Range: -7.2731
Max Act: 5.9919. Min Act: -0.1700
Data Index: 793709 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19