Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2046 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4935. Min Range: -5.4935
Max Act: 5.4935. Min Act: -0.1700
Data Index: 4615820 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4935. Min Range: -5.4935
Max Act: 5.4622. Min Act: -0.1700
Data Index: 742540 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4935. Min Range: -5.4935
Max Act: 5.2747. Min Act: -0.1700
Data Index: 698582 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4935. Min Range: -5.4935
Max Act: 5.1810. Min Act: -0.1700
Data Index: 2669571 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4935. Min Range: -5.4935
Max Act: 5.1185. Min Act: -0.1700
Data Index: 5519093 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4935. Min Range: -5.4935
Max Act: 5.1185. Min Act: -0.1700
Data Index: 6191127 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4935. Min Range: -5.4935
Max Act: 5.0560. Min Act: -0.1700
Data Index: 3570842 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4935. Min Range: -5.4935
Max Act: 5.0872. Min Act: -0.1700
Data Index: 7662544 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4935. Min Range: -5.4935
Max Act: 5.0872. Min Act: -0.1700
Data Index: 7650879 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4935. Min Range: -5.4935
Max Act: 5.0560. Min Act: -0.1700
Data Index: 1920426 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4935. Min Range: -5.4935
Max Act: 4.9622. Min Act: -0.1700
Data Index: 5075857 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4935. Min Range: -5.4935
Max Act: 4.9622. Min Act: -0.1700
Data Index: 5849019 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4935. Min Range: -5.4935
Max Act: 4.9622. Min Act: -0.1700
Data Index: 8380437 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4935. Min Range: -5.4935
Max Act: 4.9310. Min Act: -0.1700
Data Index: 1650166 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4935. Min Range: -5.4935
Max Act: 4.8997. Min Act: -0.1700
Data Index: 3061735 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4935. Min Range: -5.4935
Max Act: 4.9310. Min Act: -0.1700
Data Index: 8026263 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4935. Min Range: -5.4935
Max Act: 4.8372. Min Act: -0.1700
Data Index: 8743516 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4935. Min Range: -5.4935
Max Act: 4.8372. Min Act: -0.1700
Data Index: 6657233 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4935. Min Range: -5.4935
Max Act: 4.8060. Min Act: -0.1700
Data Index: 8110087 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4935. Min Range: -5.4935
Max Act: 4.7435. Min Act: -0.1700
Data Index: 7500752 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19