Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1321 in Layer 13
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: 7038143 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.9100. Min Act: -0.1700
Data Index: 8519218 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.8788. Min Act: -0.1700
Data Index: 6376049 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.8788. Min Act: -0.1700
Data Index: 3250064 (Open Web Text)
Max Activating Token Index: 347
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: 4100459 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.8475. Min Act: -0.1700
Data Index: 2538177 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.8163. Min Act: -0.1700
Data Index: 3419579 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.8163. Min Act: -0.1700
Data Index: 5227077 (Open Web Text)
Max Activating Token Index: 61
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: 2869568 (Open Web Text)
Max Activating Token Index: 163
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: 8449459 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.7538. Min Act: -0.1700
Data Index: 3473601 (Open Web Text)
Max Activating Token Index: 484
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: 4023718 (Open Web Text)
Max Activating Token Index: 42
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: 1184885 (Open Web Text)
Max Activating Token Index: 385
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: 2855821 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.7225. Min Act: -0.1700
Data Index: 7555701 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.7225. Min Act: -0.1700
Data Index: 5631631 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.7225. Min Act: -0.1700
Data Index: 2294144 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.6912. Min Act: -0.1700
Data Index: 4542735 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.6600. Min Act: -0.1700
Data Index: 1202946 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.6600. Min Act: -0.1700
Data Index: 8088591 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19