Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1170 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5088. Min Range: -7.5088
Max Act: 7.5088. Min Act: -0.1700
Data Index: 6449185 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5088. Min Range: -7.5088
Max Act: 7.4775. Min Act: -0.1700
Data Index: 7497247 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5088. Min Range: -7.5088
Max Act: 7.4150. Min Act: -0.1700
Data Index: 659715 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5088. Min Range: -7.5088
Max Act: 7.3838. Min Act: -0.1700
Data Index: 3020255 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5088. Min Range: -7.5088
Max Act: 7.3838. Min Act: -0.1700
Data Index: 1929850 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5088. Min Range: -7.5088
Max Act: 7.3525. Min Act: -0.1700
Data Index: 2485184 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5088. Min Range: -7.5088
Max Act: 7.3838. Min Act: -0.1700
Data Index: 8292356 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5088. Min Range: -7.5088
Max Act: 7.3525. Min Act: -0.1700
Data Index: 3100138 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5088. Min Range: -7.5088
Max Act: 7.3525. Min Act: -0.1700
Data Index: 1363112 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5088. Min Range: -7.5088
Max Act: 7.2900. Min Act: -0.1700
Data Index: 2103721 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5088. Min Range: -7.5088
Max Act: 7.3213. Min Act: -0.1700
Data Index: 2857810 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5088. Min Range: -7.5088
Max Act: 7.2900. Min Act: -0.1700
Data Index: 2347516 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5088. Min Range: -7.5088
Max Act: 7.2588. Min Act: -0.1700
Data Index: 5781462 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5088. Min Range: -7.5088
Max Act: 7.2900. Min Act: -0.1700
Data Index: 2742166 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5088. Min Range: -7.5088
Max Act: 7.2900. Min Act: -0.1700
Data Index: 6141598 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5088. Min Range: -7.5088
Max Act: 7.2588. Min Act: -0.1700
Data Index: 3195547 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5088. Min Range: -7.5088
Max Act: 7.2588. Min Act: -0.1700
Data Index: 6797424 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5088. Min Range: -7.5088
Max Act: 7.2275. Min Act: -0.1700
Data Index: 1683305 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5088. Min Range: -7.5088
Max Act: 7.2275. Min Act: -0.1700
Data Index: 7571814 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5088. Min Range: -7.5088
Max Act: 7.2275. Min Act: -0.1700
Data Index: 3073102 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19