Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3984 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0676. Min Range: -3.0676
Max Act: 3.0676. Min Act: -0.1700
Data Index: 3384924 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0676. Min Range: -3.0676
Max Act: 3.0045. Min Act: -0.1700
Data Index: 441830 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0676. Min Range: -3.0676
Max Act: 3.0045. Min Act: -0.1700
Data Index: 354749 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0676. Min Range: -3.0676
Max Act: 2.9729. Min Act: -0.1700
Data Index: 350705 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0676. Min Range: -3.0676
Max Act: 2.9729. Min Act: -0.1700
Data Index: 5003595 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0676. Min Range: -3.0676
Max Act: 2.9729. Min Act: -0.1700
Data Index: 4980513 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0676. Min Range: -3.0676
Max Act: 2.9729. Min Act: -0.1700
Data Index: 4620471 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0676. Min Range: -3.0676
Max Act: 2.9729. Min Act: -0.1700
Data Index: 4618342 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0676. Min Range: -3.0676
Max Act: 2.9412. Min Act: -0.1700
Data Index: 26 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0676. Min Range: -3.0676
Max Act: 2.9729. Min Act: -0.1700
Data Index: 56943 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0676. Min Range: -3.0676
Max Act: 2.9729. Min Act: -0.1700
Data Index: 4210727 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0676. Min Range: -3.0676
Max Act: 2.9729. Min Act: -0.1700
Data Index: 1045323 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0676. Min Range: -3.0676
Max Act: 2.9729. Min Act: -0.1700
Data Index: 3841643 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0676. Min Range: -3.0676
Max Act: 2.9412. Min Act: -0.1700
Data Index: 787071 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0676. Min Range: -3.0676
Max Act: 2.9729. Min Act: -0.1700
Data Index: 3259810 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0676. Min Range: -3.0676
Max Act: 2.9729. Min Act: -0.1700
Data Index: 2687507 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0676. Min Range: -3.0676
Max Act: 2.9729. Min Act: -0.1700
Data Index: 2669085 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0676. Min Range: -3.0676
Max Act: 2.9729. Min Act: -0.1700
Data Index: 2319962 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0676. Min Range: -3.0676
Max Act: 2.9729. Min Act: -0.1700
Data Index: 2296921 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0676. Min Range: -3.0676
Max Act: 2.9729. Min Act: -0.1700
Data Index: 1150473 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #19