Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1043 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2089. Min Range: -5.2089
Max Act: 5.2089. Min Act: -0.1700
Data Index: 6460084 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2089. Min Range: -5.2089
Max Act: 5.2089. Min Act: -0.1700
Data Index: 2449982 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2089. Min Range: -5.2089
Max Act: 5.1777. Min Act: -0.1700
Data Index: 5314571 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2089. Min Range: -5.2089
Max Act: 5.1464. Min Act: -0.1700
Data Index: 7416280 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2089. Min Range: -5.2089
Max Act: 5.1464. Min Act: -0.1700
Data Index: 3596092 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2089. Min Range: -5.2089
Max Act: 5.1152. Min Act: -0.1700
Data Index: 7777079 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2089. Min Range: -5.2089
Max Act: 5.1152. Min Act: -0.1700
Data Index: 4969057 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2089. Min Range: -5.2089
Max Act: 5.1152. Min Act: -0.1700
Data Index: 5746122 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2089. Min Range: -5.2089
Max Act: 5.1152. Min Act: -0.1700
Data Index: 2912007 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2089. Min Range: -5.2089
Max Act: 5.0839. Min Act: -0.1700
Data Index: 5857707 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2089. Min Range: -5.2089
Max Act: 5.0839. Min Act: -0.1700
Data Index: 3511506 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2089. Min Range: -5.2089
Max Act: 5.0527. Min Act: -0.1700
Data Index: 3180421 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2089. Min Range: -5.2089
Max Act: 5.0527. Min Act: -0.1700
Data Index: 4253671 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2089. Min Range: -5.2089
Max Act: 5.0527. Min Act: -0.1700
Data Index: 1224275 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2089. Min Range: -5.2089
Max Act: 5.0527. Min Act: -0.1695
Data Index: 3019637 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2089. Min Range: -5.2089
Max Act: 5.0527. Min Act: -0.1700
Data Index: 4487577 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2089. Min Range: -5.2089
Max Act: 5.0527. Min Act: -0.1700
Data Index: 8762514 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2089. Min Range: -5.2089
Max Act: 5.0214. Min Act: -0.1700
Data Index: 5767578 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2089. Min Range: -5.2089
Max Act: 5.0214. Min Act: -0.1700
Data Index: 929078 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2089. Min Range: -5.2089
Max Act: 5.0214. Min Act: -0.1700
Data Index: 2001915 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #19