Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2172 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4230. Min Range: -5.4230
Max Act: 5.4230. Min Act: -0.1700
Data Index: 376196 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4230. Min Range: -5.4230
Max Act: 5.3605. Min Act: -0.1700
Data Index: 8591900 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4230. Min Range: -5.4230
Max Act: 5.2043. Min Act: -0.1700
Data Index: 3516884 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4230. Min Range: -5.4230
Max Act: 5.2043. Min Act: -0.1700
Data Index: 8591901 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4230. Min Range: -5.4230
Max Act: 5.2043. Min Act: -0.1700
Data Index: 5370122 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4230. Min Range: -5.4230
Max Act: 5.1418. Min Act: -0.1700
Data Index: 6542003 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4230. Min Range: -5.4230
Max Act: 5.1418. Min Act: -0.1700
Data Index: 2479139 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4230. Min Range: -5.4230
Max Act: 5.1105. Min Act: -0.1700
Data Index: 4958495 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4230. Min Range: -5.4230
Max Act: 5.1418. Min Act: -0.1700
Data Index: 4363401 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4230. Min Range: -5.4230
Max Act: 5.1105. Min Act: -0.1700
Data Index: 1302751 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4230. Min Range: -5.4230
Max Act: 5.0793. Min Act: -0.1700
Data Index: 8459063 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4230. Min Range: -5.4230
Max Act: 5.0793. Min Act: -0.1700
Data Index: 1023333 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4230. Min Range: -5.4230
Max Act: 5.0793. Min Act: -0.1700
Data Index: 7107504 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4230. Min Range: -5.4230
Max Act: 5.0480. Min Act: -0.1700
Data Index: 5119177 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4230. Min Range: -5.4230
Max Act: 5.0480. Min Act: -0.1700
Data Index: 525223 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4230. Min Range: -5.4230
Max Act: 5.0480. Min Act: -0.1700
Data Index: 7443630 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4230. Min Range: -5.4230
Max Act: 5.0480. Min Act: -0.1700
Data Index: 4452699 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4230. Min Range: -5.4230
Max Act: 5.0480. Min Act: -0.1700
Data Index: 5352247 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4230. Min Range: -5.4230
Max Act: 5.0480. Min Act: -0.1700
Data Index: 4855020 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4230. Min Range: -5.4230
Max Act: 5.0168. Min Act: -0.1700
Data Index: 5720856 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19