Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3978 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8615. Min Range: -4.8615
Max Act: 4.8615. Min Act: -0.1700
Data Index: 6566199 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8615. Min Range: -4.8615
Max Act: 4.8302. Min Act: -0.1700
Data Index: 1645120 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8615. Min Range: -4.8615
Max Act: 4.7677. Min Act: -0.1700
Data Index: 4494082 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8615. Min Range: -4.8615
Max Act: 4.6740. Min Act: -0.1700
Data Index: 4315395 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8615. Min Range: -4.8615
Max Act: 4.6115. Min Act: -0.1700
Data Index: 1248091 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8615. Min Range: -4.8615
Max Act: 4.6115. Min Act: -0.1700
Data Index: 90826 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8615. Min Range: -4.8615
Max Act: 4.6115. Min Act: -0.1700
Data Index: 49745 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8615. Min Range: -4.8615
Max Act: 4.5802. Min Act: -0.1700
Data Index: 2380661 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8615. Min Range: -4.8615
Max Act: 4.5802. Min Act: -0.1700
Data Index: 6711486 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8615. Min Range: -4.8615
Max Act: 4.5490. Min Act: -0.1700
Data Index: 735425 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8615. Min Range: -4.8615
Max Act: 4.5490. Min Act: -0.1700
Data Index: 8396528 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8615. Min Range: -4.8615
Max Act: 4.5802. Min Act: -0.1700
Data Index: 2481705 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8615. Min Range: -4.8615
Max Act: 4.5802. Min Act: -0.1700
Data Index: 3028265 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8615. Min Range: -4.8615
Max Act: 4.5802. Min Act: -0.1700
Data Index: 7185252 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8615. Min Range: -4.8615
Max Act: 4.5490. Min Act: -0.1700
Data Index: 586118 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8615. Min Range: -4.8615
Max Act: 4.5490. Min Act: -0.1700
Data Index: 1382839 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8615. Min Range: -4.8615
Max Act: 4.5490. Min Act: -0.1700
Data Index: 1098773 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8615. Min Range: -4.8615
Max Act: 4.5177. Min Act: -0.1700
Data Index: 5687765 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8615. Min Range: -4.8615
Max Act: 4.5490. Min Act: -0.1700
Data Index: 4056497 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8615. Min Range: -4.8615
Max Act: 4.5490. Min Act: -0.1700
Data Index: 4289846 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19