Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4037 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7093. Min Range: -2.7093
Max Act: 2.6933. Min Act: -0.1700
Data Index: 7532922 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7093. Min Range: -2.7093
Max Act: 2.7093. Min Act: -0.1700
Data Index: 6672366 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7093. Min Range: -2.7093
Max Act: 2.6933. Min Act: -0.1700
Data Index: 6722658 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7093. Min Range: -2.7093
Max Act: 2.6452. Min Act: -0.1700
Data Index: 1669387 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7093. Min Range: -2.7093
Max Act: 2.6292. Min Act: -0.1700
Data Index: 4835678 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7093. Min Range: -2.7093
Max Act: 2.6131. Min Act: -0.1700
Data Index: 1693113 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7093. Min Range: -2.7093
Max Act: 2.6131. Min Act: -0.1700
Data Index: 1121109 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7093. Min Range: -2.7093
Max Act: 2.5970. Min Act: -0.1700
Data Index: 8067781 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7093. Min Range: -2.7093
Max Act: 2.5970. Min Act: -0.1700
Data Index: 8139780 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7093. Min Range: -2.7093
Max Act: 2.5970. Min Act: -0.1700
Data Index: 5746184 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7093. Min Range: -2.7093
Max Act: 2.5487. Min Act: -0.1700
Data Index: 7156563 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7093. Min Range: -2.7093
Max Act: 2.5163. Min Act: -0.1700
Data Index: 8676303 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7093. Min Range: -2.7093
Max Act: 2.5163. Min Act: -0.1700
Data Index: 7506552 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7093. Min Range: -2.7093
Max Act: 2.5001. Min Act: -0.1700
Data Index: 8807440 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7093. Min Range: -2.7093
Max Act: 2.5001. Min Act: -0.1700
Data Index: 987426 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7093. Min Range: -2.7093
Max Act: 2.5163. Min Act: -0.1700
Data Index: 967309 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7093. Min Range: -2.7093
Max Act: 2.4839. Min Act: -0.1700
Data Index: 8489406 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7093. Min Range: -2.7093
Max Act: 2.4677. Min Act: -0.1700
Data Index: 6133744 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7093. Min Range: -2.7093
Max Act: 2.4677. Min Act: -0.1700
Data Index: 4353542 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7093. Min Range: -2.7093
Max Act: 2.4677. Min Act: -0.1700
Data Index: 1127270 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19