Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1698 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0701. Min Range: -7.0701
Max Act: 7.0701. Min Act: -0.1700
Data Index: 5259950 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0701. Min Range: -7.0701
Max Act: 6.7889. Min Act: -0.1700
Data Index: 4456979 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0701. Min Range: -7.0701
Max Act: 6.6639. Min Act: -0.1700
Data Index: 8124413 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0701. Min Range: -7.0701
Max Act: 6.6951. Min Act: -0.1700
Data Index: 5273377 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0701. Min Range: -7.0701
Max Act: 6.6326. Min Act: -0.1700
Data Index: 492672 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0701. Min Range: -7.0701
Max Act: 6.5389. Min Act: -0.1700
Data Index: 5436004 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0701. Min Range: -7.0701
Max Act: 6.5076. Min Act: -0.1700
Data Index: 7881655 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0701. Min Range: -7.0701
Max Act: 6.4139. Min Act: -0.1700
Data Index: 6174807 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0701. Min Range: -7.0701
Max Act: 6.3514. Min Act: -0.1700
Data Index: 1071560 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0701. Min Range: -7.0701
Max Act: 6.3201. Min Act: -0.1700
Data Index: 4564991 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0701. Min Range: -7.0701
Max Act: 6.3201. Min Act: -0.1700
Data Index: 4654419 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0701. Min Range: -7.0701
Max Act: 6.3201. Min Act: -0.1700
Data Index: 1836941 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0701. Min Range: -7.0701
Max Act: 6.3201. Min Act: -0.1700
Data Index: 167301 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0701. Min Range: -7.0701
Max Act: 6.3201. Min Act: -0.1700
Data Index: 2486296 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0701. Min Range: -7.0701
Max Act: 6.2889. Min Act: -0.1700
Data Index: 7279773 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0701. Min Range: -7.0701
Max Act: 6.2576. Min Act: -0.1700
Data Index: 461791 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0701. Min Range: -7.0701
Max Act: 6.2576. Min Act: -0.1700
Data Index: 4122430 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0701. Min Range: -7.0701
Max Act: 6.2264. Min Act: -0.1700
Data Index: 4808174 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0701. Min Range: -7.0701
Max Act: 6.2264. Min Act: -0.1700
Data Index: 4093782 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0701. Min Range: -7.0701
Max Act: 6.2576. Min Act: -0.1700
Data Index: 8166818 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19