Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 76 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6782. Min Range: -5.6782
Max Act: 5.6782. Min Act: -0.1700
Data Index: 8468442 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6782. Min Range: -5.6782
Max Act: 5.3657. Min Act: -0.1700
Data Index: 6688676 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6782. Min Range: -5.6782
Max Act: 5.3032. Min Act: -0.1700
Data Index: 7667892 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6782. Min Range: -5.6782
Max Act: 5.3032. Min Act: -0.1700
Data Index: 179279 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6782. Min Range: -5.6782
Max Act: 5.2094. Min Act: -0.1700
Data Index: 6726345 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6782. Min Range: -5.6782
Max Act: 5.2407. Min Act: -0.1700
Data Index: 5433362 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6782. Min Range: -5.6782
Max Act: 5.2094. Min Act: -0.1700
Data Index: 6559527 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6782. Min Range: -5.6782
Max Act: 5.2094. Min Act: -0.1700
Data Index: 4738415 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6782. Min Range: -5.6782
Max Act: 5.1782. Min Act: -0.1700
Data Index: 4977167 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6782. Min Range: -5.6782
Max Act: 5.1782. Min Act: -0.1700
Data Index: 3556566 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6782. Min Range: -5.6782
Max Act: 5.1469. Min Act: -0.1700
Data Index: 8322629 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6782. Min Range: -5.6782
Max Act: 5.1469. Min Act: -0.1700
Data Index: 4148380 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6782. Min Range: -5.6782
Max Act: 5.1469. Min Act: -0.1700
Data Index: 7558443 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6782. Min Range: -5.6782
Max Act: 5.1469. Min Act: -0.1700
Data Index: 6763286 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6782. Min Range: -5.6782
Max Act: 5.1469. Min Act: -0.1700
Data Index: 975942 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6782. Min Range: -5.6782
Max Act: 5.1157. Min Act: -0.1700
Data Index: 4848702 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6782. Min Range: -5.6782
Max Act: 5.1157. Min Act: -0.1700
Data Index: 3556299 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6782. Min Range: -5.6782
Max Act: 5.1157. Min Act: -0.1700
Data Index: 5695163 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6782. Min Range: -5.6782
Max Act: 5.1157. Min Act: -0.1700
Data Index: 6538694 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6782. Min Range: -5.6782
Max Act: 5.1157. Min Act: -0.1700
Data Index: 2327250 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19