Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4923 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.5944. Min Act: -0.1699
Data Index: 5770236 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.5631. Min Act: -0.1700
Data Index: 1620376 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.5319. Min Act: -0.1700
Data Index: 4790772 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.5319. Min Act: -0.1700
Data Index: 2647198 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.5319. Min Act: -0.1700
Data Index: 497493 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.4694. Min Act: -0.1700
Data Index: 5943957 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.5006. Min Act: -0.1700
Data Index: 8064911 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.5006. Min Act: -0.1700
Data Index: 2667390 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.4694. Min Act: -0.1700
Data Index: 1514985 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.4694. Min Act: -0.1700
Data Index: 2025487 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.4381. Min Act: -0.1700
Data Index: 167511 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.4694. Min Act: -0.1699
Data Index: 7241284 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.4694. Min Act: -0.1699
Data Index: 6868268 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.4694. Min Act: -0.1700
Data Index: 6443768 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.4694. Min Act: -0.1700
Data Index: 3896200 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.4694. Min Act: -0.1700
Data Index: 2695685 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.4381. Min Act: -0.1686
Data Index: 2412376 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.4694. Min Act: -0.1693
Data Index: 4029989 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.4381. Min Act: -0.1699
Data Index: 3308690 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5944. Min Range: -5.5944
Max Act: 5.4381. Min Act: -0.1700
Data Index: 1152159 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19