Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1224 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3756. Min Range: -5.3756
Max Act: 5.3756. Min Act: -0.1700
Data Index: 2487163 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3756. Min Range: -5.3756
Max Act: 5.3756. Min Act: -0.1700
Data Index: 6442641 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3756. Min Range: -5.3756
Max Act: 5.3444. Min Act: -0.1700
Data Index: 2999447 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3756. Min Range: -5.3756
Max Act: 5.2506. Min Act: -0.1700
Data Index: 7740857 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3756. Min Range: -5.3756
Max Act: 5.1256. Min Act: -0.1700
Data Index: 5702436 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3756. Min Range: -5.3756
Max Act: 5.0944. Min Act: -0.1700
Data Index: 7948025 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3756. Min Range: -5.3756
Max Act: 5.0944. Min Act: -0.1700
Data Index: 1953415 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3756. Min Range: -5.3756
Max Act: 5.0319. Min Act: -0.1700
Data Index: 5702435 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3756. Min Range: -5.3756
Max Act: 5.0631. Min Act: -0.1700
Data Index: 6045953 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3756. Min Range: -5.3756
Max Act: 5.0631. Min Act: -0.1700
Data Index: 8446245 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3756. Min Range: -5.3756
Max Act: 5.0319. Min Act: -0.1700
Data Index: 2629604 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3756. Min Range: -5.3756
Max Act: 5.0319. Min Act: -0.1700
Data Index: 4282990 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3756. Min Range: -5.3756
Max Act: 5.0006. Min Act: -0.1700
Data Index: 2919773 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3756. Min Range: -5.3756
Max Act: 4.9694. Min Act: -0.1700
Data Index: 8730269 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3756. Min Range: -5.3756
Max Act: 4.9694. Min Act: -0.1700
Data Index: 4282986 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3756. Min Range: -5.3756
Max Act: 4.9381. Min Act: -0.1700
Data Index: 6122721 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3756. Min Range: -5.3756
Max Act: 4.9694. Min Act: -0.1700
Data Index: 3140921 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3756. Min Range: -5.3756
Max Act: 4.9694. Min Act: -0.1700
Data Index: 1751482 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3756. Min Range: -5.3756
Max Act: 4.9694. Min Act: -0.1700
Data Index: 164014 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3756. Min Range: -5.3756
Max Act: 4.9381. Min Act: -0.1700
Data Index: 1980006 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19