Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 20 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5163. Min Range: -5.5163
Max Act: 5.5163. Min Act: -0.1700
Data Index: 5823074 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5163. Min Range: -5.5163
Max Act: 5.4226. Min Act: -0.1700
Data Index: 6393720 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5163. Min Range: -5.5163
Max Act: 5.4226. Min Act: -0.1700
Data Index: 1160048 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5163. Min Range: -5.5163
Max Act: 5.2663. Min Act: -0.1700
Data Index: 8008795 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5163. Min Range: -5.5163
Max Act: 5.2663. Min Act: -0.1700
Data Index: 4066090 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5163. Min Range: -5.5163
Max Act: 5.2351. Min Act: -0.1700
Data Index: 7427560 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5163. Min Range: -5.5163
Max Act: 5.2351. Min Act: -0.1700
Data Index: 6273056 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5163. Min Range: -5.5163
Max Act: 5.1726. Min Act: -0.1700
Data Index: 2844817 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5163. Min Range: -5.5163
Max Act: 5.1413. Min Act: -0.1700
Data Index: 2536324 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5163. Min Range: -5.5163
Max Act: 5.1101. Min Act: -0.1700
Data Index: 7754785 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5163. Min Range: -5.5163
Max Act: 5.0788. Min Act: -0.1700
Data Index: 6397457 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5163. Min Range: -5.5163
Max Act: 5.0476. Min Act: -0.1700
Data Index: 3874762 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5163. Min Range: -5.5163
Max Act: 5.0163. Min Act: -0.1700
Data Index: 8687160 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5163. Min Range: -5.5163
Max Act: 5.0163. Min Act: -0.1700
Data Index: 4950397 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5163. Min Range: -5.5163
Max Act: 4.9851. Min Act: -0.1700
Data Index: 8525410 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5163. Min Range: -5.5163
Max Act: 4.9851. Min Act: -0.1700
Data Index: 2878874 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5163. Min Range: -5.5163
Max Act: 4.9851. Min Act: -0.1700
Data Index: 6044330 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5163. Min Range: -5.5163
Max Act: 4.9851. Min Act: -0.1700
Data Index: 627523 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5163. Min Range: -5.5163
Max Act: 4.9851. Min Act: -0.1700
Data Index: 3423097 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5163. Min Range: -5.5163
Max Act: 4.9538. Min Act: -0.1700
Data Index: 3466102 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19