Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1070 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7691. Min Range: -1.7691
Max Act: 1.7691. Min Act: -0.1700
Data Index: 4087023 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7691. Min Range: -1.7691
Max Act: 1.7518. Min Act: -0.1700
Data Index: 5893101 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7691. Min Range: -1.7691
Max Act: 1.7172. Min Act: -0.1700
Data Index: 8218022 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7691. Min Range: -1.7691
Max Act: 1.7086. Min Act: -0.1700
Data Index: 812282 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7691. Min Range: -1.7691
Max Act: 1.6912. Min Act: -0.1700
Data Index: 297322 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7691. Min Range: -1.7691
Max Act: 1.7086. Min Act: -0.1699
Data Index: 2485966 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7691. Min Range: -1.7691
Max Act: 1.7086. Min Act: -0.1698
Data Index: 1877914 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7691. Min Range: -1.7691
Max Act: 1.6912. Min Act: -0.1700
Data Index: 6396649 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7691. Min Range: -1.7691
Max Act: 1.6739. Min Act: -0.1699
Data Index: 6461081 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7691. Min Range: -1.7691
Max Act: 1.6999. Min Act: -0.1699
Data Index: 2268719 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7691. Min Range: -1.7691
Max Act: 1.6652. Min Act: -0.1700
Data Index: 1351073 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7691. Min Range: -1.7691
Max Act: 1.6652. Min Act: -0.1700
Data Index: 5187542 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7691. Min Range: -1.7691
Max Act: 1.6739. Min Act: -0.1700
Data Index: 3657372 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7691. Min Range: -1.7691
Max Act: 1.6652. Min Act: -0.1700
Data Index: 6293688 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7691. Min Range: -1.7691
Max Act: 1.6652. Min Act: -0.1700
Data Index: 7567452 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7691. Min Range: -1.7691
Max Act: 1.6652. Min Act: -0.1700
Data Index: 1631990 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7691. Min Range: -1.7691
Max Act: 1.6565. Min Act: -0.1700
Data Index: 5864416 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7691. Min Range: -1.7691
Max Act: 1.6652. Min Act: -0.1700
Data Index: 3081799 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7691. Min Range: -1.7691
Max Act: 1.6652. Min Act: -0.1690
Data Index: 2116147 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7691. Min Range: -1.7691
Max Act: 1.6565. Min Act: -0.1700
Data Index: 2803466 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19