Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1653 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1154. Min Range: -4.1154
Max Act: 4.1154. Min Act: -0.1700
Data Index: 4846069 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1154. Min Range: -4.1154
Max Act: 4.0529. Min Act: -0.1700
Data Index: 6485836 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1154. Min Range: -4.1154
Max Act: 4.0529. Min Act: -0.1700
Data Index: 5715668 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1154. Min Range: -4.1154
Max Act: 3.9279. Min Act: -0.1700
Data Index: 5715648 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1154. Min Range: -4.1154
Max Act: 3.9279. Min Act: -0.1700
Data Index: 3552287 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1154. Min Range: -4.1154
Max Act: 3.9122. Min Act: -0.1700
Data Index: 1545610 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1154. Min Range: -4.1154
Max Act: 3.8966. Min Act: -0.1700
Data Index: 3557038 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1154. Min Range: -4.1154
Max Act: 3.8966. Min Act: -0.1700
Data Index: 6143054 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1154. Min Range: -4.1154
Max Act: 3.8653. Min Act: -0.1700
Data Index: 1863963 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1154. Min Range: -4.1154
Max Act: 3.8810. Min Act: -0.1700
Data Index: 5613242 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1154. Min Range: -4.1154
Max Act: 3.8497. Min Act: -0.1700
Data Index: 6818863 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1154. Min Range: -4.1154
Max Act: 3.8653. Min Act: -0.1700
Data Index: 5893557 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1154. Min Range: -4.1154
Max Act: 3.8341. Min Act: -0.1700
Data Index: 5715664 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1154. Min Range: -4.1154
Max Act: 3.8184. Min Act: -0.1700
Data Index: 3304828 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1154. Min Range: -4.1154
Max Act: 3.8184. Min Act: -0.1700
Data Index: 4113009 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1154. Min Range: -4.1154
Max Act: 3.8341. Min Act: -0.1700
Data Index: 5232710 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1154. Min Range: -4.1154
Max Act: 3.8028. Min Act: -0.1700
Data Index: 8249326 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1154. Min Range: -4.1154
Max Act: 3.8028. Min Act: -0.1700
Data Index: 1209683 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1154. Min Range: -4.1154
Max Act: 3.7715. Min Act: -0.1700
Data Index: 3361416 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1154. Min Range: -4.1154
Max Act: 3.7715. Min Act: -0.1700
Data Index: 1146276 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19