Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2346 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5081. Min Range: -7.5081
Max Act: 7.5081. Min Act: -0.1700
Data Index: 2000967 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5081. Min Range: -7.5081
Max Act: 7.3206. Min Act: -0.1700
Data Index: 8553341 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5081. Min Range: -7.5081
Max Act: 7.3206. Min Act: -0.1700
Data Index: 6144050 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5081. Min Range: -7.5081
Max Act: 7.2893. Min Act: -0.1700
Data Index: 3939797 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5081. Min Range: -7.5081
Max Act: 7.2268. Min Act: -0.1700
Data Index: 7924959 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5081. Min Range: -7.5081
Max Act: 7.2581. Min Act: -0.1700
Data Index: 2000962 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5081. Min Range: -7.5081
Max Act: 7.1956. Min Act: -0.1700
Data Index: 3158583 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5081. Min Range: -7.5081
Max Act: 7.2268. Min Act: -0.1700
Data Index: 1150931 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5081. Min Range: -7.5081
Max Act: 7.1643. Min Act: -0.1700
Data Index: 3746450 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5081. Min Range: -7.5081
Max Act: 7.1331. Min Act: -0.1700
Data Index: 5827836 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5081. Min Range: -7.5081
Max Act: 7.1643. Min Act: -0.1700
Data Index: 3144611 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5081. Min Range: -7.5081
Max Act: 7.0706. Min Act: -0.1700
Data Index: 3346003 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5081. Min Range: -7.5081
Max Act: 7.0393. Min Act: -0.1700
Data Index: 6309124 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5081. Min Range: -7.5081
Max Act: 7.0081. Min Act: -0.1700
Data Index: 8241470 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5081. Min Range: -7.5081
Max Act: 7.0081. Min Act: -0.1700
Data Index: 393834 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5081. Min Range: -7.5081
Max Act: 7.0081. Min Act: -0.1700
Data Index: 5408970 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5081. Min Range: -7.5081
Max Act: 7.0081. Min Act: -0.1700
Data Index: 1631115 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5081. Min Range: -7.5081
Max Act: 6.9768. Min Act: -0.1700
Data Index: 3645673 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5081. Min Range: -7.5081
Max Act: 6.9143. Min Act: -0.1700
Data Index: 5842404 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5081. Min Range: -7.5081
Max Act: 6.9143. Min Act: -0.1700
Data Index: 6014696 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19