Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 936 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7562. Min Range: -5.7562
Max Act: 5.7562. Min Act: -0.1700
Data Index: 7095 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7562. Min Range: -5.7562
Max Act: 5.7249. Min Act: -0.1700
Data Index: 7627526 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7562. Min Range: -5.7562
Max Act: 5.6937. Min Act: -0.1700
Data Index: 6114981 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7562. Min Range: -5.7562
Max Act: 5.6624. Min Act: -0.1700
Data Index: 3153856 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7562. Min Range: -5.7562
Max Act: 5.6624. Min Act: -0.1700
Data Index: 7433203 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7562. Min Range: -5.7562
Max Act: 5.6312. Min Act: -0.1700
Data Index: 3243461 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7562. Min Range: -5.7562
Max Act: 5.5687. Min Act: -0.1700
Data Index: 7805871 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7562. Min Range: -5.7562
Max Act: 5.5687. Min Act: -0.1700
Data Index: 437129 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7562. Min Range: -5.7562
Max Act: 5.5687. Min Act: -0.1700
Data Index: 6727255 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7562. Min Range: -5.7562
Max Act: 5.5374. Min Act: -0.1700
Data Index: 4229256 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7562. Min Range: -5.7562
Max Act: 5.5374. Min Act: -0.1700
Data Index: 8216622 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7562. Min Range: -5.7562
Max Act: 5.5374. Min Act: -0.1700
Data Index: 5935554 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7562. Min Range: -5.7562
Max Act: 5.5374. Min Act: -0.1700
Data Index: 376698 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7562. Min Range: -5.7562
Max Act: 5.5062. Min Act: -0.1700
Data Index: 224687 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7562. Min Range: -5.7562
Max Act: 5.5062. Min Act: -0.1700
Data Index: 147572 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7562. Min Range: -5.7562
Max Act: 5.5062. Min Act: -0.1700
Data Index: 93241 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7562. Min Range: -5.7562
Max Act: 5.5062. Min Act: -0.1700
Data Index: 1408125 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7562. Min Range: -5.7562
Max Act: 5.5062. Min Act: -0.1700
Data Index: 6543147 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7562. Min Range: -5.7562
Max Act: 5.4749. Min Act: -0.1700
Data Index: 5304924 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7562. Min Range: -5.7562
Max Act: 5.4749. Min Act: -0.1700
Data Index: 7440909 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19