Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1819 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.4730. Min Range: -8.4730
Max Act: 8.4730. Min Act: -0.1700
Data Index: 7746555 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4730. Min Range: -8.4730
Max Act: 8.4105. Min Act: -0.1700
Data Index: 5236377 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4730. Min Range: -8.4730
Max Act: 8.4105. Min Act: -0.1700
Data Index: 8164365 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4730. Min Range: -8.4730
Max Act: 8.3480. Min Act: -0.1700
Data Index: 4352357 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4730. Min Range: -8.4730
Max Act: 8.2230. Min Act: -0.1700
Data Index: 3764837 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4730. Min Range: -8.4730
Max Act: 8.2230. Min Act: -0.1700
Data Index: 24608 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4730. Min Range: -8.4730
Max Act: 8.2230. Min Act: -0.1700
Data Index: 2987850 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4730. Min Range: -8.4730
Max Act: 8.2230. Min Act: -0.1700
Data Index: 1253339 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4730. Min Range: -8.4730
Max Act: 8.2230. Min Act: -0.1700
Data Index: 2841921 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4730. Min Range: -8.4730
Max Act: 8.1605. Min Act: -0.1700
Data Index: 4956860 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4730. Min Range: -8.4730
Max Act: 8.1605. Min Act: -0.1700
Data Index: 1212161 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4730. Min Range: -8.4730
Max Act: 8.1605. Min Act: -0.1700
Data Index: 8653285 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4730. Min Range: -8.4730
Max Act: 8.1605. Min Act: -0.1700
Data Index: 1212172 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4730. Min Range: -8.4730
Max Act: 8.0980. Min Act: -0.1700
Data Index: 5101748 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4730. Min Range: -8.4730
Max Act: 8.0980. Min Act: -0.1700
Data Index: 1091042 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4730. Min Range: -8.4730
Max Act: 8.0980. Min Act: -0.1700
Data Index: 7390957 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4730. Min Range: -8.4730
Max Act: 8.0980. Min Act: -0.1700
Data Index: 4729903 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4730. Min Range: -8.4730
Max Act: 8.0980. Min Act: -0.1700
Data Index: 2641213 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4730. Min Range: -8.4730
Max Act: 7.9730. Min Act: -0.1700
Data Index: 3471814 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4730. Min Range: -8.4730
Max Act: 7.9105. Min Act: -0.1700
Data Index: 803664 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19