Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2774 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.3482. Min Act: -0.1700
Data Index: 4012227 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.3169. Min Act: -0.1700
Data Index: 7484138 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.1294. Min Act: -0.1700
Data Index: 4012229 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.0982. Min Act: -0.1700
Data Index: 1749921 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.0982. Min Act: -0.1700
Data Index: 6929499 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.0669. Min Act: -0.1700
Data Index: 478643 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.0044. Min Act: -0.1700
Data Index: 1600047 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3482. Min Range: -5.3482
Max Act: 4.9732. Min Act: -0.1700
Data Index: 5781223 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3482. Min Range: -5.3482
Max Act: 4.8794. Min Act: -0.1700
Data Index: 7262036 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3482. Min Range: -5.3482
Max Act: 4.9107. Min Act: -0.1700
Data Index: 1749922 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3482. Min Range: -5.3482
Max Act: 4.8794. Min Act: -0.1700
Data Index: 5781227 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3482. Min Range: -5.3482
Max Act: 4.7857. Min Act: -0.1700
Data Index: 4390615 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3482. Min Range: -5.3482
Max Act: 4.8169. Min Act: -0.1700
Data Index: 362831 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3482. Min Range: -5.3482
Max Act: 4.7544. Min Act: -0.1700
Data Index: 5657249 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3482. Min Range: -5.3482
Max Act: 4.6607. Min Act: -0.1700
Data Index: 3989049 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3482. Min Range: -5.3482
Max Act: 4.6607. Min Act: -0.1700
Data Index: 5403710 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3482. Min Range: -5.3482
Max Act: 4.6607. Min Act: -0.1700
Data Index: 7032115 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3482. Min Range: -5.3482
Max Act: 4.5669. Min Act: -0.1700
Data Index: 388375 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3482. Min Range: -5.3482
Max Act: 4.5669. Min Act: -0.1699
Data Index: 40367 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3482. Min Range: -5.3482
Max Act: 4.5357. Min Act: -0.1700
Data Index: 3801448 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19