Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2852 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0089. Min Range: -5.0089
Max Act: 5.0089. Min Act: -0.1700
Data Index: 3764987 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0089. Min Range: -5.0089
Max Act: 4.9151. Min Act: -0.1700
Data Index: 4593407 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0089. Min Range: -5.0089
Max Act: 4.8839. Min Act: -0.1700
Data Index: 1436897 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0089. Min Range: -5.0089
Max Act: 4.8839. Min Act: -0.1700
Data Index: 7290102 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0089. Min Range: -5.0089
Max Act: 4.7589. Min Act: -0.1700
Data Index: 1268254 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0089. Min Range: -5.0089
Max Act: 4.6651. Min Act: -0.1700
Data Index: 8814788 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0089. Min Range: -5.0089
Max Act: 4.6964. Min Act: -0.1700
Data Index: 796388 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0089. Min Range: -5.0089
Max Act: 4.6651. Min Act: -0.1700
Data Index: 688281 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0089. Min Range: -5.0089
Max Act: 4.5714. Min Act: -0.1700
Data Index: 7591882 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0089. Min Range: -5.0089
Max Act: 4.6026. Min Act: -0.1700
Data Index: 198827 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0089. Min Range: -5.0089
Max Act: 4.5714. Min Act: -0.1700
Data Index: 6787798 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0089. Min Range: -5.0089
Max Act: 4.6026. Min Act: -0.1700
Data Index: 3764988 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0089. Min Range: -5.0089
Max Act: 4.5714. Min Act: -0.1700
Data Index: 1268250 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0089. Min Range: -5.0089
Max Act: 4.5401. Min Act: -0.1700
Data Index: 8400597 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0089. Min Range: -5.0089
Max Act: 4.5401. Min Act: -0.1700
Data Index: 8735616 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0089. Min Range: -5.0089
Max Act: 4.5401. Min Act: -0.1700
Data Index: 8814787 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0089. Min Range: -5.0089
Max Act: 4.4776. Min Act: -0.1700
Data Index: 7062447 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0089. Min Range: -5.0089
Max Act: 4.4464. Min Act: -0.1700
Data Index: 1908199 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0089. Min Range: -5.0089
Max Act: 4.4776. Min Act: -0.1700
Data Index: 6244984 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0089. Min Range: -5.0089
Max Act: 4.5401. Min Act: -0.1700
Data Index: 2022800 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19