Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 457 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5999. Min Range: -6.5999
Max Act: 6.5999. Min Act: -0.1700
Data Index: 3851429 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5999. Min Range: -6.5999
Max Act: 6.4749. Min Act: -0.1700
Data Index: 1268495 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5999. Min Range: -6.5999
Max Act: 6.4749. Min Act: -0.1700
Data Index: 675993 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5999. Min Range: -6.5999
Max Act: 6.4749. Min Act: -0.1700
Data Index: 675982 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5999. Min Range: -6.5999
Max Act: 6.4749. Min Act: -0.1698
Data Index: 1585057 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5999. Min Range: -6.5999
Max Act: 6.4749. Min Act: -0.1700
Data Index: 3501312 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5999. Min Range: -6.5999
Max Act: 6.4749. Min Act: -0.1698
Data Index: 3501329 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5999. Min Range: -6.5999
Max Act: 6.4749. Min Act: -0.1697
Data Index: 781105 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5999. Min Range: -6.5999
Max Act: 6.4749. Min Act: -0.1699
Data Index: 3194163 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5999. Min Range: -6.5999
Max Act: 6.4749. Min Act: -0.1700
Data Index: 2967000 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5999. Min Range: -6.5999
Max Act: 6.4749. Min Act: -0.1700
Data Index: 2966998 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5999. Min Range: -6.5999
Max Act: 6.4749. Min Act: -0.1697
Data Index: 1268484 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5999. Min Range: -6.5999
Max Act: 6.4749. Min Act: -0.1689
Data Index: 840455 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5999. Min Range: -6.5999
Max Act: 6.4749. Min Act: -0.1697
Data Index: 2934706 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5999. Min Range: -6.5999
Max Act: 6.4749. Min Act: -0.1698
Data Index: 2934711 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5999. Min Range: -6.5999
Max Act: 6.4749. Min Act: -0.1699
Data Index: 2734900 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5999. Min Range: -6.5999
Max Act: 6.4749. Min Act: -0.1689
Data Index: 2403253 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5999. Min Range: -6.5999
Max Act: 6.4749. Min Act: -0.1700
Data Index: 303604 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5999. Min Range: -6.5999
Max Act: 6.4749. Min Act: -0.1693
Data Index: 2010919 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5999. Min Range: -6.5999
Max Act: 6.4749. Min Act: -0.1700
Data Index: 1783905 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19