Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4455 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2051. Min Range: -4.2051
Max Act: 4.2051. Min Act: -0.1700
Data Index: 2364746 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2051. Min Range: -4.2051
Max Act: 4.1426. Min Act: -0.1700
Data Index: 8693978 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2051. Min Range: -4.2051
Max Act: 4.1113. Min Act: -0.1700
Data Index: 11340 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2051. Min Range: -4.2051
Max Act: 4.1113. Min Act: -0.1700
Data Index: 5514623 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2051. Min Range: -4.2051
Max Act: 4.1113. Min Act: -0.1700
Data Index: 6462833 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2051. Min Range: -4.2051
Max Act: 4.1113. Min Act: -0.1700
Data Index: 7340987 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2051. Min Range: -4.2051
Max Act: 4.0488. Min Act: -0.1700
Data Index: 5322235 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2051. Min Range: -4.2051
Max Act: 4.0488. Min Act: -0.1700
Data Index: 6850529 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2051. Min Range: -4.2051
Max Act: 4.0175. Min Act: -0.1700
Data Index: 5635854 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2051. Min Range: -4.2051
Max Act: 4.0175. Min Act: -0.1700
Data Index: 5931933 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2051. Min Range: -4.2051
Max Act: 3.9863. Min Act: -0.1700
Data Index: 6388198 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2051. Min Range: -4.2051
Max Act: 3.9863. Min Act: -0.1700
Data Index: 2095197 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2051. Min Range: -4.2051
Max Act: 3.9863. Min Act: -0.1700
Data Index: 3954061 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2051. Min Range: -4.2051
Max Act: 3.9863. Min Act: -0.1700
Data Index: 1265187 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2051. Min Range: -4.2051
Max Act: 3.9550. Min Act: -0.1700
Data Index: 5093979 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2051. Min Range: -4.2051
Max Act: 3.9550. Min Act: -0.1700
Data Index: 3525025 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2051. Min Range: -4.2051
Max Act: 3.9550. Min Act: -0.1700
Data Index: 6781455 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2051. Min Range: -4.2051
Max Act: 3.9550. Min Act: -0.1700
Data Index: 1113058 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2051. Min Range: -4.2051
Max Act: 3.9550. Min Act: -0.1700
Data Index: 6809761 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2051. Min Range: -4.2051
Max Act: 3.9863. Min Act: -0.1700
Data Index: 5671919 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19