Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5250 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9966. Min Range: -3.9966
Max Act: 3.9966. Min Act: -0.1700
Data Index: 8391375 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9966. Min Range: -3.9966
Max Act: 3.9653. Min Act: -0.1700
Data Index: 1713178 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9966. Min Range: -3.9966
Max Act: 3.9340. Min Act: -0.1700
Data Index: 2652415 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9966. Min Range: -3.9966
Max Act: 3.9340. Min Act: -0.1700
Data Index: 2821105 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9966. Min Range: -3.9966
Max Act: 3.9340. Min Act: -0.1700
Data Index: 1829502 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9966. Min Range: -3.9966
Max Act: 3.8715. Min Act: -0.1700
Data Index: 4578174 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9966. Min Range: -3.9966
Max Act: 3.8402. Min Act: -0.1700
Data Index: 5039698 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9966. Min Range: -3.9966
Max Act: 3.8715. Min Act: -0.1700
Data Index: 39992 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9966. Min Range: -3.9966
Max Act: 3.9028. Min Act: -0.1700
Data Index: 3134577 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9966. Min Range: -3.9966
Max Act: 3.8715. Min Act: -0.1700
Data Index: 2592695 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9966. Min Range: -3.9966
Max Act: 3.8402. Min Act: -0.1700
Data Index: 8818110 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9966. Min Range: -3.9966
Max Act: 3.8715. Min Act: -0.1700
Data Index: 498499 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9966. Min Range: -3.9966
Max Act: 3.8715. Min Act: -0.1700
Data Index: 3478421 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9966. Min Range: -3.9966
Max Act: 3.8402. Min Act: -0.1700
Data Index: 2405603 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9966. Min Range: -3.9966
Max Act: 3.8090. Min Act: -0.1700
Data Index: 6910850 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9966. Min Range: -3.9966
Max Act: 3.8402. Min Act: -0.1700
Data Index: 6696223 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9966. Min Range: -3.9966
Max Act: 3.8402. Min Act: -0.1700
Data Index: 5802141 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9966. Min Range: -3.9966
Max Act: 3.8402. Min Act: -0.1700
Data Index: 2789325 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9966. Min Range: -3.9966
Max Act: 3.8090. Min Act: -0.1700
Data Index: 5241325 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9966. Min Range: -3.9966
Max Act: 3.8402. Min Act: -0.1700
Data Index: 6387870 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19