Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2462 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1579. Min Range: -5.1579
Max Act: 5.1579. Min Act: -0.1700
Data Index: 6585064 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1579. Min Range: -5.1579
Max Act: 5.0954. Min Act: -0.1700
Data Index: 1124254 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1579. Min Range: -5.1579
Max Act: 5.0641. Min Act: -0.1700
Data Index: 2939708 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1579. Min Range: -5.1579
Max Act: 5.0641. Min Act: -0.1700
Data Index: 3210356 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1579. Min Range: -5.1579
Max Act: 5.0641. Min Act: -0.1700
Data Index: 1808952 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1579. Min Range: -5.1579
Max Act: 5.0641. Min Act: -0.1700
Data Index: 6257884 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1579. Min Range: -5.1579
Max Act: 5.0329. Min Act: -0.1700
Data Index: 7042109 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1579. Min Range: -5.1579
Max Act: 5.0329. Min Act: -0.1700
Data Index: 4709548 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1579. Min Range: -5.1579
Max Act: 5.0329. Min Act: -0.1700
Data Index: 7221615 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1579. Min Range: -5.1579
Max Act: 5.0329. Min Act: -0.1700
Data Index: 4079440 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1579. Min Range: -5.1579
Max Act: 5.0016. Min Act: -0.1700
Data Index: 19500 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1579. Min Range: -5.1579
Max Act: 5.0016. Min Act: -0.1700
Data Index: 6612037 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1579. Min Range: -5.1579
Max Act: 5.0016. Min Act: -0.1700
Data Index: 3102832 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1579. Min Range: -5.1579
Max Act: 5.0016. Min Act: -0.1700
Data Index: 1995398 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1579. Min Range: -5.1579
Max Act: 5.0016. Min Act: -0.1700
Data Index: 6044196 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1579. Min Range: -5.1579
Max Act: 5.0329. Min Act: -0.1700
Data Index: 8631964 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1579. Min Range: -5.1579
Max Act: 5.0016. Min Act: -0.1700
Data Index: 5833214 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1579. Min Range: -5.1579
Max Act: 5.0016. Min Act: -0.1700
Data Index: 2642713 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1579. Min Range: -5.1579
Max Act: 4.9704. Min Act: -0.1700
Data Index: 944070 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1579. Min Range: -5.1579
Max Act: 4.9704. Min Act: -0.1700
Data Index: 1043158 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #19