Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3867 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4455. Min Range: -9.4455
Max Act: 9.4455. Min Act: -0.1700
Data Index: 4727276 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4455. Min Range: -9.4455
Max Act: 9.3205. Min Act: -0.1700
Data Index: 7301409 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4455. Min Range: -9.4455
Max Act: 9.1955. Min Act: -0.1700
Data Index: 7265968 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4455. Min Range: -9.4455
Max Act: 9.1330. Min Act: -0.1700
Data Index: 866497 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4455. Min Range: -9.4455
Max Act: 9.1955. Min Act: -0.1700
Data Index: 4332433 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4455. Min Range: -9.4455
Max Act: 9.1330. Min Act: -0.1700
Data Index: 6413836 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4455. Min Range: -9.4455
Max Act: 9.0705. Min Act: -0.1700
Data Index: 3154917 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4455. Min Range: -9.4455
Max Act: 9.0705. Min Act: -0.1700
Data Index: 3342831 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4455. Min Range: -9.4455
Max Act: 9.0705. Min Act: -0.1700
Data Index: 3606792 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4455. Min Range: -9.4455
Max Act: 9.0705. Min Act: -0.1700
Data Index: 6882384 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4455. Min Range: -9.4455
Max Act: 8.9455. Min Act: -0.1700
Data Index: 747933 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4455. Min Range: -9.4455
Max Act: 9.0080. Min Act: -0.1700
Data Index: 4585776 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4455. Min Range: -9.4455
Max Act: 9.0080. Min Act: -0.1700
Data Index: 5775393 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4455. Min Range: -9.4455
Max Act: 8.9455. Min Act: -0.1700
Data Index: 4746068 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4455. Min Range: -9.4455
Max Act: 9.0080. Min Act: -0.1700
Data Index: 8403073 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4455. Min Range: -9.4455
Max Act: 8.8830. Min Act: -0.1700
Data Index: 6278142 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4455. Min Range: -9.4455
Max Act: 8.8830. Min Act: -0.1700
Data Index: 5542288 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4455. Min Range: -9.4455
Max Act: 8.8830. Min Act: -0.1700
Data Index: 1482874 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4455. Min Range: -9.4455
Max Act: 8.8830. Min Act: -0.1700
Data Index: 2346302 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4455. Min Range: -9.4455
Max Act: 8.8830. Min Act: -0.1700
Data Index: 6797684 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19