Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2697 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8095. Min Range: -5.8095
Max Act: 5.8095. Min Act: -0.1700
Data Index: 7555527 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8095. Min Range: -5.8095
Max Act: 5.7157. Min Act: -0.1700
Data Index: 7555536 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8095. Min Range: -5.8095
Max Act: 5.6532. Min Act: -0.1700
Data Index: 8094989 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8095. Min Range: -5.8095
Max Act: 5.6220. Min Act: -0.1700
Data Index: 1633741 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8095. Min Range: -5.8095
Max Act: 5.5907. Min Act: -0.1697
Data Index: 7555532 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8095. Min Range: -5.8095
Max Act: 5.5907. Min Act: -0.1699
Data Index: 7555531 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8095. Min Range: -5.8095
Max Act: 5.5907. Min Act: -0.1700
Data Index: 229744 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8095. Min Range: -5.8095
Max Act: 5.5282. Min Act: -0.1700
Data Index: 7689274 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8095. Min Range: -5.8095
Max Act: 5.4970. Min Act: -0.1700
Data Index: 266712 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8095. Min Range: -5.8095
Max Act: 5.5282. Min Act: -0.1699
Data Index: 1069761 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8095. Min Range: -5.8095
Max Act: 5.5282. Min Act: -0.1700
Data Index: 4773058 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8095. Min Range: -5.8095
Max Act: 5.4970. Min Act: -0.1700
Data Index: 1069756 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8095. Min Range: -5.8095
Max Act: 5.4657. Min Act: -0.1700
Data Index: 1069760 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8095. Min Range: -5.8095
Max Act: 5.4032. Min Act: -0.1700
Data Index: 7053438 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8095. Min Range: -5.8095
Max Act: 5.4032. Min Act: -0.1700
Data Index: 7465067 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8095. Min Range: -5.8095
Max Act: 5.4032. Min Act: -0.1700
Data Index: 8094982 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8095. Min Range: -5.8095
Max Act: 5.4032. Min Act: -0.1700
Data Index: 330322 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8095. Min Range: -5.8095
Max Act: 5.4345. Min Act: -0.1700
Data Index: 5465499 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8095. Min Range: -5.8095
Max Act: 5.4345. Min Act: -0.1698
Data Index: 7555526 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8095. Min Range: -5.8095
Max Act: 5.3720. Min Act: -0.1700
Data Index: 6273373 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19