Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1157 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2061. Min Range: -7.2061
Max Act: 7.2061. Min Act: -0.1700
Data Index: 7438027 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2061. Min Range: -7.2061
Max Act: 7.0811. Min Act: -0.1700
Data Index: 2603821 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2061. Min Range: -7.2061
Max Act: 6.9561. Min Act: -0.1700
Data Index: 7437653 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2061. Min Range: -7.2061
Max Act: 6.8623. Min Act: -0.1700
Data Index: 7361264 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2061. Min Range: -7.2061
Max Act: 6.8623. Min Act: -0.1700
Data Index: 2243380 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2061. Min Range: -7.2061
Max Act: 6.7686. Min Act: -0.1700
Data Index: 6409054 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2061. Min Range: -7.2061
Max Act: 6.7061. Min Act: -0.1700
Data Index: 979672 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2061. Min Range: -7.2061
Max Act: 6.7061. Min Act: -0.1700
Data Index: 3132917 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2061. Min Range: -7.2061
Max Act: 6.6748. Min Act: -0.1700
Data Index: 8203509 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2061. Min Range: -7.2061
Max Act: 6.6748. Min Act: -0.1700
Data Index: 6103613 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2061. Min Range: -7.2061
Max Act: 6.6436. Min Act: -0.1700
Data Index: 7517279 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2061. Min Range: -7.2061
Max Act: 6.6748. Min Act: -0.1700
Data Index: 406038 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2061. Min Range: -7.2061
Max Act: 6.6123. Min Act: -0.1700
Data Index: 2277445 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2061. Min Range: -7.2061
Max Act: 6.6436. Min Act: -0.1700
Data Index: 1725483 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2061. Min Range: -7.2061
Max Act: 6.5811. Min Act: -0.1700
Data Index: 1675863 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2061. Min Range: -7.2061
Max Act: 6.5186. Min Act: -0.1700
Data Index: 1465353 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2061. Min Range: -7.2061
Max Act: 6.5498. Min Act: -0.1700
Data Index: 885339 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2061. Min Range: -7.2061
Max Act: 6.5186. Min Act: -0.1700
Data Index: 3333168 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2061. Min Range: -7.2061
Max Act: 6.5186. Min Act: -0.1700
Data Index: 3171039 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2061. Min Range: -7.2061
Max Act: 6.5186. Min Act: -0.1700
Data Index: 7346193 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19