Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1643 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7677. Min Range: -3.7677
Max Act: 3.7677. Min Act: -0.1700
Data Index: 2418414 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7677. Min Range: -3.7677
Max Act: 3.7520. Min Act: -0.1700
Data Index: 4921651 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7677. Min Range: -3.7677
Max Act: 3.7677. Min Act: -0.1700
Data Index: 7745063 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7677. Min Range: -3.7677
Max Act: 3.7051. Min Act: -0.1700
Data Index: 6206858 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7677. Min Range: -3.7677
Max Act: 3.6425. Min Act: -0.1700
Data Index: 5208744 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7677. Min Range: -3.7677
Max Act: 3.6425. Min Act: -0.1700
Data Index: 2020598 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7677. Min Range: -3.7677
Max Act: 3.6425. Min Act: -0.1700
Data Index: 3530970 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7677. Min Range: -3.7677
Max Act: 3.6425. Min Act: -0.1700
Data Index: 1297114 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7677. Min Range: -3.7677
Max Act: 3.6269. Min Act: -0.1700
Data Index: 4078103 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7677. Min Range: -3.7677
Max Act: 3.5956. Min Act: -0.1700
Data Index: 1881395 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7677. Min Range: -3.7677
Max Act: 3.6112. Min Act: -0.1700
Data Index: 6820548 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7677. Min Range: -3.7677
Max Act: 3.5956. Min Act: -0.1700
Data Index: 1992737 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7677. Min Range: -3.7677
Max Act: 3.5799. Min Act: -0.1700
Data Index: 1945330 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7677. Min Range: -3.7677
Max Act: 3.5799. Min Act: -0.1700
Data Index: 2886325 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7677. Min Range: -3.7677
Max Act: 3.5643. Min Act: -0.1700
Data Index: 2173730 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7677. Min Range: -3.7677
Max Act: 3.5486. Min Act: -0.1700
Data Index: 6853306 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7677. Min Range: -3.7677
Max Act: 3.5330. Min Act: -0.1700
Data Index: 5470740 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7677. Min Range: -3.7677
Max Act: 3.5330. Min Act: -0.1700
Data Index: 2947800 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7677. Min Range: -3.7677
Max Act: 3.5330. Min Act: -0.1700
Data Index: 5953556 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7677. Min Range: -3.7677
Max Act: 3.5330. Min Act: -0.1700
Data Index: 7453419 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19