Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5039 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.9413. Min Act: -0.1700
Data Index: 2198040 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.9101. Min Act: -0.1700
Data Index: 7928972 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.9101. Min Act: -0.1700
Data Index: 8757376 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.8476. Min Act: -0.1700
Data Index: 260301 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.8788. Min Act: -0.1700
Data Index: 5091597 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.8788. Min Act: -0.1700
Data Index: 4703711 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.8476. Min Act: -0.1700
Data Index: 7681618 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.8476. Min Act: -0.1700
Data Index: 6534487 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.8163. Min Act: -0.1700
Data Index: 3867492 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.8163. Min Act: -0.1700
Data Index: 3040977 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.7851. Min Act: -0.1700
Data Index: 387537 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.7538. Min Act: -0.1700
Data Index: 268634 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.7538. Min Act: -0.1700
Data Index: 6305642 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.7538. Min Act: -0.1700
Data Index: 8462027 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.7226. Min Act: -0.1700
Data Index: 5657857 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.7226. Min Act: -0.1700
Data Index: 5738478 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.7226. Min Act: -0.1700
Data Index: 6910373 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.7538. Min Act: -0.1700
Data Index: 7074549 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.7226. Min Act: -0.1700
Data Index: 7500914 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.7226. Min Act: -0.1700
Data Index: 2055161 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #19