Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2725 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1699. Min Range: -4.1699
Max Act: 4.1699. Min Act: -0.1700
Data Index: 2127158 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1699. Min Range: -4.1699
Max Act: 4.1074. Min Act: -0.1700
Data Index: 714891 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1699. Min Range: -4.1699
Max Act: 4.0761. Min Act: -0.1700
Data Index: 2298930 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1699. Min Range: -4.1699
Max Act: 4.1074. Min Act: -0.1700
Data Index: 7760149 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1699. Min Range: -4.1699
Max Act: 4.0449. Min Act: -0.1700
Data Index: 7146316 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1699. Min Range: -4.1699
Max Act: 4.0136. Min Act: -0.1700
Data Index: 8748118 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1699. Min Range: -4.1699
Max Act: 3.9980. Min Act: -0.1700
Data Index: 4577276 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1699. Min Range: -4.1699
Max Act: 4.0136. Min Act: -0.1700
Data Index: 5936705 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1699. Min Range: -4.1699
Max Act: 3.9823. Min Act: -0.1700
Data Index: 3528825 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1699. Min Range: -4.1699
Max Act: 3.9980. Min Act: -0.1700
Data Index: 3974330 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1699. Min Range: -4.1699
Max Act: 3.9980. Min Act: -0.1700
Data Index: 5115416 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1699. Min Range: -4.1699
Max Act: 3.9667. Min Act: -0.1700
Data Index: 2732279 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1699. Min Range: -4.1699
Max Act: 3.9667. Min Act: -0.1700
Data Index: 6230176 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1699. Min Range: -4.1699
Max Act: 3.9667. Min Act: -0.1700
Data Index: 7893641 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1699. Min Range: -4.1699
Max Act: 3.9667. Min Act: -0.1700
Data Index: 7246318 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1699. Min Range: -4.1699
Max Act: 3.9511. Min Act: -0.1700
Data Index: 4328487 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1699. Min Range: -4.1699
Max Act: 3.9511. Min Act: -0.1700
Data Index: 2355431 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1699. Min Range: -4.1699
Max Act: 3.9667. Min Act: -0.1700
Data Index: 8180939 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1699. Min Range: -4.1699
Max Act: 3.9354. Min Act: -0.1700
Data Index: 6350789 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1699. Min Range: -4.1699
Max Act: 3.9198. Min Act: -0.1700
Data Index: 4619755 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19