Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2781 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.9418. Min Act: -0.1700
Data Index: 1922783 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.7230. Min Act: -0.1700
Data Index: 3005530 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.6293. Min Act: -0.1700
Data Index: 4527195 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.5980. Min Act: -0.1700
Data Index: 356127 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.5355. Min Act: -0.1700
Data Index: 7776093 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.4418. Min Act: -0.1700
Data Index: 3947286 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.4418. Min Act: -0.1700
Data Index: 8042281 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.3793. Min Act: -0.1700
Data Index: 4187684 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.3480. Min Act: -0.1700
Data Index: 2822355 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.3480. Min Act: -0.1700
Data Index: 2283211 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.3480. Min Act: -0.1700
Data Index: 2054272 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.3168. Min Act: -0.1700
Data Index: 7828577 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.2543. Min Act: -0.1700
Data Index: 1928069 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.2855. Min Act: -0.1700
Data Index: 4336200 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.2855. Min Act: -0.1700
Data Index: 3090437 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.2230. Min Act: -0.1700
Data Index: 162092 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.2855. Min Act: -0.1700
Data Index: 8737758 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.1918. Min Act: -0.1700
Data Index: 5175092 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.2543. Min Act: -0.1700
Data Index: 7037192 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.1918. Min Act: -0.1700
Data Index: 5863677 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19