Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3077 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.8659. Min Act: -0.1700
Data Index: 2414330 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.8659. Min Act: -0.1700
Data Index: 3845431 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.8347. Min Act: -0.1700
Data Index: 6584027 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.8034. Min Act: -0.1700
Data Index: 125254 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.8034. Min Act: -0.1700
Data Index: 7644411 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.7722. Min Act: -0.1700
Data Index: 7564327 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.7722. Min Act: -0.1700
Data Index: 751956 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.7409. Min Act: -0.1700
Data Index: 7918658 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.7409. Min Act: -0.1700
Data Index: 3231394 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.7409. Min Act: -0.1700
Data Index: 576034 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.6784. Min Act: -0.1700
Data Index: 8564825 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.6784. Min Act: -0.1700
Data Index: 849589 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.6472. Min Act: -0.1700
Data Index: 576033 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.6472. Min Act: -0.1700
Data Index: 4556360 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.6472. Min Act: -0.1700
Data Index: 7040431 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.6472. Min Act: -0.1700
Data Index: 2689198 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.5847. Min Act: -0.1700
Data Index: 2939066 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.6159. Min Act: -0.1700
Data Index: 389904 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.6472. Min Act: -0.1700
Data Index: 170663 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8659. Min Range: -5.8659
Max Act: 5.5847. Min Act: -0.1700
Data Index: 7564326 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19