Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3073 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.7739. Min Act: -0.1700
Data Index: 5673314 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.5235. Min Act: -0.1700
Data Index: 3265590 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.5235. Min Act: -0.1700
Data Index: 7100073 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.4765. Min Act: -0.1700
Data Index: 6404757 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.4765. Min Act: -0.1700
Data Index: 1785365 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.4608. Min Act: -0.1700
Data Index: 1910656 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.4452. Min Act: -0.1700
Data Index: 3016423 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.4452. Min Act: -0.1700
Data Index: 2389231 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.4295. Min Act: -0.1700
Data Index: 7100072 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.4295. Min Act: -0.1700
Data Index: 7048719 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.3825. Min Act: -0.1700
Data Index: 1437017 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.3511. Min Act: -0.1700
Data Index: 492615 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.3511. Min Act: -0.1700
Data Index: 2151160 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.3511. Min Act: -0.1700
Data Index: 746168 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.3040. Min Act: -0.1700
Data Index: 2081643 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.3040. Min Act: -0.1700
Data Index: 2678477 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.2883. Min Act: -0.1700
Data Index: 576332 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.3040. Min Act: -0.1700
Data Index: 5788118 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.3040. Min Act: -0.1700
Data Index: 622060 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7739. Min Range: -3.7739
Max Act: 3.2883. Min Act: -0.1700
Data Index: 7467622 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19