Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5707 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0766. Min Range: -6.0766
Max Act: 6.0766. Min Act: -0.1700
Data Index: 1288008 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0766. Min Range: -6.0766
Max Act: 5.9828. Min Act: -0.1700
Data Index: 978494 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0766. Min Range: -6.0766
Max Act: 5.9203. Min Act: -0.1700
Data Index: 2891125 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0766. Min Range: -6.0766
Max Act: 5.9203. Min Act: -0.1700
Data Index: 6553271 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0766. Min Range: -6.0766
Max Act: 5.7328. Min Act: -0.1700
Data Index: 3826821 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0766. Min Range: -6.0766
Max Act: 5.7016. Min Act: -0.1700
Data Index: 1073390 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0766. Min Range: -6.0766
Max Act: 5.6703. Min Act: -0.1700
Data Index: 1501155 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0766. Min Range: -6.0766
Max Act: 5.6703. Min Act: -0.1700
Data Index: 6500840 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0766. Min Range: -6.0766
Max Act: 5.6391. Min Act: -0.1700
Data Index: 703247 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0766. Min Range: -6.0766
Max Act: 5.6078. Min Act: -0.1700
Data Index: 5216385 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0766. Min Range: -6.0766
Max Act: 5.6391. Min Act: -0.1700
Data Index: 4231183 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0766. Min Range: -6.0766
Max Act: 5.6391. Min Act: -0.1700
Data Index: 4989141 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0766. Min Range: -6.0766
Max Act: 5.6078. Min Act: -0.1700
Data Index: 133378 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0766. Min Range: -6.0766
Max Act: 5.6078. Min Act: -0.1700
Data Index: 2588977 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0766. Min Range: -6.0766
Max Act: 5.5766. Min Act: -0.1700
Data Index: 445723 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0766. Min Range: -6.0766
Max Act: 5.5453. Min Act: -0.1700
Data Index: 3802811 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0766. Min Range: -6.0766
Max Act: 5.5141. Min Act: -0.1700
Data Index: 221241 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0766. Min Range: -6.0766
Max Act: 5.4828. Min Act: -0.1700
Data Index: 1642046 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0766. Min Range: -6.0766
Max Act: 5.5141. Min Act: -0.1700
Data Index: 4892652 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0766. Min Range: -6.0766
Max Act: 5.5141. Min Act: -0.1700
Data Index: 1442289 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19