Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1248 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2961. Min Range: -9.2961
Max Act: 9.2961. Min Act: -0.1700
Data Index: 6069968 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2961. Min Range: -9.2961
Max Act: 9.2336. Min Act: -0.1700
Data Index: 1123436 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2961. Min Range: -9.2961
Max Act: 9.1711. Min Act: -0.1700
Data Index: 8396416 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2961. Min Range: -9.2961
Max Act: 9.1086. Min Act: -0.1700
Data Index: 4003960 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2961. Min Range: -9.2961
Max Act: 9.1086. Min Act: -0.1700
Data Index: 4078999 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2961. Min Range: -9.2961
Max Act: 9.0461. Min Act: -0.1700
Data Index: 2571528 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2961. Min Range: -9.2961
Max Act: 8.9836. Min Act: -0.1700
Data Index: 8345674 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2961. Min Range: -9.2961
Max Act: 8.9211. Min Act: -0.1700
Data Index: 4963108 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2961. Min Range: -9.2961
Max Act: 8.9836. Min Act: -0.1700
Data Index: 335857 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2961. Min Range: -9.2961
Max Act: 8.8586. Min Act: -0.1700
Data Index: 1255805 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2961. Min Range: -9.2961
Max Act: 8.8586. Min Act: -0.1700
Data Index: 1901525 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2961. Min Range: -9.2961
Max Act: 8.7961. Min Act: -0.1700
Data Index: 3428778 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2961. Min Range: -9.2961
Max Act: 8.7961. Min Act: -0.1700
Data Index: 4280856 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2961. Min Range: -9.2961
Max Act: 8.7961. Min Act: -0.1700
Data Index: 6969761 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2961. Min Range: -9.2961
Max Act: 8.7336. Min Act: -0.1700
Data Index: 8637756 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2961. Min Range: -9.2961
Max Act: 8.7336. Min Act: -0.1700
Data Index: 8251043 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2961. Min Range: -9.2961
Max Act: 8.7961. Min Act: -0.1700
Data Index: 5010171 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2961. Min Range: -9.2961
Max Act: 8.7336. Min Act: -0.1700
Data Index: 615759 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2961. Min Range: -9.2961
Max Act: 8.7961. Min Act: -0.1700
Data Index: 3557543 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2961. Min Range: -9.2961
Max Act: 8.7336. Min Act: -0.1700
Data Index: 2328877 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19