Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1632 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4608. Min Range: -4.4608
Max Act: 4.4608. Min Act: -0.1700
Data Index: 5133600 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4608. Min Range: -4.4608
Max Act: 4.4295. Min Act: -0.1700
Data Index: 7837571 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4608. Min Range: -4.4608
Max Act: 4.4608. Min Act: -0.1700
Data Index: 2599909 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4608. Min Range: -4.4608
Max Act: 4.3983. Min Act: -0.1700
Data Index: 3943570 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4608. Min Range: -4.4608
Max Act: 4.3983. Min Act: -0.1700
Data Index: 1818203 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4608. Min Range: -4.4608
Max Act: 4.3670. Min Act: -0.1700
Data Index: 4898088 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4608. Min Range: -4.4608
Max Act: 4.3358. Min Act: -0.1700
Data Index: 3955864 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4608. Min Range: -4.4608
Max Act: 4.4295. Min Act: -0.1700
Data Index: 6385448 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4608. Min Range: -4.4608
Max Act: 4.3358. Min Act: -0.1700
Data Index: 3881703 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4608. Min Range: -4.4608
Max Act: 4.3358. Min Act: -0.1700
Data Index: 1028135 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4608. Min Range: -4.4608
Max Act: 4.2733. Min Act: -0.1699
Data Index: 8602651 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4608. Min Range: -4.4608
Max Act: 4.3045. Min Act: -0.1700
Data Index: 8055708 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4608. Min Range: -4.4608
Max Act: 4.1795. Min Act: -0.1700
Data Index: 3185551 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4608. Min Range: -4.4608
Max Act: 4.2420. Min Act: -0.1700
Data Index: 4511196 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4608. Min Range: -4.4608
Max Act: 4.3045. Min Act: -0.1699
Data Index: 6712967 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4608. Min Range: -4.4608
Max Act: 4.2420. Min Act: -0.1700
Data Index: 6576334 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4608. Min Range: -4.4608
Max Act: 4.2108. Min Act: -0.1700
Data Index: 1544622 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4608. Min Range: -4.4608
Max Act: 4.2420. Min Act: -0.1699
Data Index: 5764108 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4608. Min Range: -4.4608
Max Act: 4.2733. Min Act: -0.1700
Data Index: 731750 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4608. Min Range: -4.4608
Max Act: 4.2108. Min Act: -0.1700
Data Index: 4252900 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #19