Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3668 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7837. Min Range: -5.7837
Max Act: 5.7837. Min Act: -0.1700
Data Index: 7917007 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7837. Min Range: -5.7837
Max Act: 5.5649. Min Act: -0.1700
Data Index: 7822894 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7837. Min Range: -5.7837
Max Act: 5.5337. Min Act: -0.1700
Data Index: 4924280 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7837. Min Range: -5.7837
Max Act: 5.5337. Min Act: -0.1700
Data Index: 130490 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7837. Min Range: -5.7837
Max Act: 5.5337. Min Act: -0.1700
Data Index: 1811883 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7837. Min Range: -5.7837
Max Act: 5.5337. Min Act: -0.1700
Data Index: 7917009 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7837. Min Range: -5.7837
Max Act: 5.5024. Min Act: -0.1700
Data Index: 4153122 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7837. Min Range: -5.7837
Max Act: 5.4712. Min Act: -0.1700
Data Index: 4540588 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7837. Min Range: -5.7837
Max Act: 5.5024. Min Act: -0.1700
Data Index: 1817900 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7837. Min Range: -5.7837
Max Act: 5.5024. Min Act: -0.1700
Data Index: 3586651 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7837. Min Range: -5.7837
Max Act: 5.4712. Min Act: -0.1700
Data Index: 2531339 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7837. Min Range: -5.7837
Max Act: 5.4712. Min Act: -0.1700
Data Index: 68980 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7837. Min Range: -5.7837
Max Act: 5.4712. Min Act: -0.1700
Data Index: 4752691 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7837. Min Range: -5.7837
Max Act: 5.4712. Min Act: -0.1700
Data Index: 7601819 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7837. Min Range: -5.7837
Max Act: 5.4399. Min Act: -0.1700
Data Index: 8176218 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7837. Min Range: -5.7837
Max Act: 5.4399. Min Act: -0.1700
Data Index: 4082171 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7837. Min Range: -5.7837
Max Act: 5.4399. Min Act: -0.1700
Data Index: 1817901 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7837. Min Range: -5.7837
Max Act: 5.4399. Min Act: -0.1700
Data Index: 1171152 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7837. Min Range: -5.7837
Max Act: 5.4087. Min Act: -0.1700
Data Index: 3728306 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7837. Min Range: -5.7837
Max Act: 5.4087. Min Act: -0.1700
Data Index: 2531331 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19