Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2286 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8033. Min Range: -5.8033
Max Act: 5.8033. Min Act: -0.1700
Data Index: 7837728 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8033. Min Range: -5.8033
Max Act: 5.6158. Min Act: -0.1700
Data Index: 3883900 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8033. Min Range: -5.8033
Max Act: 5.4908. Min Act: -0.1700
Data Index: 4876132 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8033. Min Range: -5.8033
Max Act: 5.5221. Min Act: -0.1700
Data Index: 2030258 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8033. Min Range: -5.8033
Max Act: 5.4908. Min Act: -0.1700
Data Index: 3252231 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8033. Min Range: -5.8033
Max Act: 5.4596. Min Act: -0.1700
Data Index: 2581461 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8033. Min Range: -5.8033
Max Act: 5.4596. Min Act: -0.1700
Data Index: 8178821 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8033. Min Range: -5.8033
Max Act: 5.4283. Min Act: -0.1700
Data Index: 6386532 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8033. Min Range: -5.8033
Max Act: 5.4283. Min Act: -0.1700
Data Index: 6367349 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8033. Min Range: -5.8033
Max Act: 5.4283. Min Act: -0.1700
Data Index: 813381 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8033. Min Range: -5.8033
Max Act: 5.4283. Min Act: -0.1700
Data Index: 380057 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8033. Min Range: -5.8033
Max Act: 5.4283. Min Act: -0.1700
Data Index: 6856033 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8033. Min Range: -5.8033
Max Act: 5.3971. Min Act: -0.1700
Data Index: 6406571 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8033. Min Range: -5.8033
Max Act: 5.3971. Min Act: -0.1700
Data Index: 4604485 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8033. Min Range: -5.8033
Max Act: 5.3658. Min Act: -0.1700
Data Index: 4275825 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8033. Min Range: -5.8033
Max Act: 5.3658. Min Act: -0.1700
Data Index: 5728382 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8033. Min Range: -5.8033
Max Act: 5.3346. Min Act: -0.1700
Data Index: 7827707 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8033. Min Range: -5.8033
Max Act: 5.3346. Min Act: -0.1700
Data Index: 3562320 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8033. Min Range: -5.8033
Max Act: 5.3033. Min Act: -0.1700
Data Index: 3875581 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8033. Min Range: -5.8033
Max Act: 5.3033. Min Act: -0.1700
Data Index: 2019160 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19