Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4470 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.4929. Min Range: -7.4929
Max Act: 7.4929. Min Act: -0.1700
Data Index: 5553030 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4929. Min Range: -7.4929
Max Act: 7.4304. Min Act: -0.1700
Data Index: 2944842 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4929. Min Range: -7.4929
Max Act: 7.4304. Min Act: -0.1700
Data Index: 522074 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4929. Min Range: -7.4929
Max Act: 7.3054. Min Act: -0.1700
Data Index: 6234513 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4929. Min Range: -7.4929
Max Act: 7.2741. Min Act: -0.1700
Data Index: 1756851 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4929. Min Range: -7.4929
Max Act: 7.2116. Min Act: -0.1700
Data Index: 3724497 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4929. Min Range: -7.4929
Max Act: 7.2116. Min Act: -0.1700
Data Index: 6673336 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4929. Min Range: -7.4929
Max Act: 7.2116. Min Act: -0.1700
Data Index: 1142719 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4929. Min Range: -7.4929
Max Act: 7.2116. Min Act: -0.1700
Data Index: 8607413 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4929. Min Range: -7.4929
Max Act: 7.1491. Min Act: -0.1700
Data Index: 8586848 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4929. Min Range: -7.4929
Max Act: 7.1491. Min Act: -0.1700
Data Index: 2155856 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4929. Min Range: -7.4929
Max Act: 7.2116. Min Act: -0.1700
Data Index: 3533101 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4929. Min Range: -7.4929
Max Act: 7.1804. Min Act: -0.1700
Data Index: 75211 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4929. Min Range: -7.4929
Max Act: 7.1491. Min Act: -0.1700
Data Index: 5709434 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4929. Min Range: -7.4929
Max Act: 7.1804. Min Act: -0.1700
Data Index: 8593907 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4929. Min Range: -7.4929
Max Act: 7.0866. Min Act: -0.1700
Data Index: 1063288 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4929. Min Range: -7.4929
Max Act: 7.1179. Min Act: -0.1700
Data Index: 6247327 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4929. Min Range: -7.4929
Max Act: 7.0866. Min Act: -0.1700
Data Index: 4933226 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4929. Min Range: -7.4929
Max Act: 7.0554. Min Act: -0.1700
Data Index: 6409878 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4929. Min Range: -7.4929
Max Act: 7.0554. Min Act: -0.1700
Data Index: 7028091 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19