Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4486 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.8474. Min Act: -0.1700
Data Index: 6290458 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.7849. Min Act: -0.1700
Data Index: 3211437 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.7537. Min Act: -0.1700
Data Index: 1274542 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.7537. Min Act: -0.1700
Data Index: 7671601 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.7537. Min Act: -0.1700
Data Index: 3211439 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.7224. Min Act: -0.1700
Data Index: 570519 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.7224. Min Act: -0.1700
Data Index: 2414875 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.7224. Min Act: -0.1700
Data Index: 5345864 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.6599. Min Act: -0.1700
Data Index: 3669626 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.6599. Min Act: -0.1700
Data Index: 2633360 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.6599. Min Act: -0.1700
Data Index: 3021593 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.6599. Min Act: -0.1700
Data Index: 7514649 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.6599. Min Act: -0.1700
Data Index: 7404224 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.5974. Min Act: -0.1700
Data Index: 6298657 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.6287. Min Act: -0.1700
Data Index: 4822737 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.6287. Min Act: -0.1700
Data Index: 7265054 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.6287. Min Act: -0.1700
Data Index: 2814956 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.6287. Min Act: -0.1700
Data Index: 3848170 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.6287. Min Act: -0.1700
Data Index: 2588065 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8474. Min Range: -4.8474
Max Act: 4.6287. Min Act: -0.1700
Data Index: 98895 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19