Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5859 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9421. Min Range: -5.9421
Max Act: 5.9421. Min Act: -0.1700
Data Index: 7802593 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9421. Min Range: -5.9421
Max Act: 5.8171. Min Act: -0.1700
Data Index: 1060928 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9421. Min Range: -5.9421
Max Act: 5.6921. Min Act: -0.1700
Data Index: 3739908 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9421. Min Range: -5.9421
Max Act: 5.6608. Min Act: -0.1700
Data Index: 3057000 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9421. Min Range: -5.9421
Max Act: 5.5671. Min Act: -0.1700
Data Index: 898259 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9421. Min Range: -5.9421
Max Act: 5.5671. Min Act: -0.1700
Data Index: 6204403 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9421. Min Range: -5.9421
Max Act: 5.5671. Min Act: -0.1700
Data Index: 8444315 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9421. Min Range: -5.9421
Max Act: 5.4733. Min Act: -0.1700
Data Index: 2887285 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9421. Min Range: -5.9421
Max Act: 5.4733. Min Act: -0.1700
Data Index: 6488768 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9421. Min Range: -5.9421
Max Act: 5.4733. Min Act: -0.1700
Data Index: 3763807 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9421. Min Range: -5.9421
Max Act: 5.4108. Min Act: -0.1700
Data Index: 1560572 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9421. Min Range: -5.9421
Max Act: 5.4108. Min Act: -0.1700
Data Index: 2962699 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9421. Min Range: -5.9421
Max Act: 5.4108. Min Act: -0.1700
Data Index: 2764753 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9421. Min Range: -5.9421
Max Act: 5.3796. Min Act: -0.1700
Data Index: 8698023 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9421. Min Range: -5.9421
Max Act: 5.3796. Min Act: -0.1700
Data Index: 7519948 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9421. Min Range: -5.9421
Max Act: 5.3483. Min Act: -0.1700
Data Index: 5059410 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9421. Min Range: -5.9421
Max Act: 5.3796. Min Act: -0.1700
Data Index: 2167802 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9421. Min Range: -5.9421
Max Act: 5.3483. Min Act: -0.1700
Data Index: 2801660 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9421. Min Range: -5.9421
Max Act: 5.3171. Min Act: -0.1700
Data Index: 8812816 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9421. Min Range: -5.9421
Max Act: 5.3483. Min Act: -0.1700
Data Index: 7918956 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19