Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 884 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6837. Min Range: -5.6837
Max Act: 5.6837. Min Act: -0.1700
Data Index: 1561315 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6837. Min Range: -5.6837
Max Act: 5.6837. Min Act: -0.1700
Data Index: 468887 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6837. Min Range: -5.6837
Max Act: 5.5899. Min Act: -0.1700
Data Index: 73657 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6837. Min Range: -5.6837
Max Act: 5.5587. Min Act: -0.1700
Data Index: 4538433 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6837. Min Range: -5.6837
Max Act: 5.5587. Min Act: -0.1700
Data Index: 1771654 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6837. Min Range: -5.6837
Max Act: 5.4962. Min Act: -0.1700
Data Index: 5129889 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6837. Min Range: -5.6837
Max Act: 5.4962. Min Act: -0.1700
Data Index: 8053781 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6837. Min Range: -5.6837
Max Act: 5.4649. Min Act: -0.1700
Data Index: 3363917 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6837. Min Range: -5.6837
Max Act: 5.4337. Min Act: -0.1700
Data Index: 143644 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6837. Min Range: -5.6837
Max Act: 5.4649. Min Act: -0.1700
Data Index: 3540692 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6837. Min Range: -5.6837
Max Act: 5.4649. Min Act: -0.1700
Data Index: 191642 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6837. Min Range: -5.6837
Max Act: 5.4024. Min Act: -0.1700
Data Index: 251096 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6837. Min Range: -5.6837
Max Act: 5.4337. Min Act: -0.1700
Data Index: 3364304 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6837. Min Range: -5.6837
Max Act: 5.4024. Min Act: -0.1700
Data Index: 4779166 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6837. Min Range: -5.6837
Max Act: 5.3399. Min Act: -0.1700
Data Index: 5346920 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6837. Min Range: -5.6837
Max Act: 5.4024. Min Act: -0.1700
Data Index: 5218976 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6837. Min Range: -5.6837
Max Act: 5.4024. Min Act: -0.1700
Data Index: 3770963 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6837. Min Range: -5.6837
Max Act: 5.3399. Min Act: -0.1700
Data Index: 8181051 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6837. Min Range: -5.6837
Max Act: 5.3399. Min Act: -0.1700
Data Index: 1385613 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6837. Min Range: -5.6837
Max Act: 5.3712. Min Act: -0.1700
Data Index: 4297333 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19