Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3057 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.7564. Min Range: -10.7564
Max Act: 10.7564. Min Act: -0.1700
Data Index: 2530310 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7564. Min Range: -10.7564
Max Act: 10.3189. Min Act: -0.1700
Data Index: 7536758 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7564. Min Range: -10.7564
Max Act: 9.9439. Min Act: -0.1700
Data Index: 3566208 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7564. Min Range: -10.7564
Max Act: 9.8189. Min Act: -0.1700
Data Index: 7135522 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7564. Min Range: -10.7564
Max Act: 9.7564. Min Act: -0.1700
Data Index: 3579628 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7564. Min Range: -10.7564
Max Act: 9.7564. Min Act: -0.1700
Data Index: 6008604 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7564. Min Range: -10.7564
Max Act: 9.7564. Min Act: -0.1700
Data Index: 5913207 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7564. Min Range: -10.7564
Max Act: 9.7564. Min Act: -0.1700
Data Index: 3646948 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7564. Min Range: -10.7564
Max Act: 9.7564. Min Act: -0.1700
Data Index: 1660268 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7564. Min Range: -10.7564
Max Act: 9.8189. Min Act: -0.1700
Data Index: 5506027 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7564. Min Range: -10.7564
Max Act: 9.6939. Min Act: -0.1700
Data Index: 1426819 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7564. Min Range: -10.7564
Max Act: 9.6939. Min Act: -0.1700
Data Index: 2273480 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7564. Min Range: -10.7564
Max Act: 9.6314. Min Act: -0.1700
Data Index: 1090096 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7564. Min Range: -10.7564
Max Act: 9.6314. Min Act: -0.1700
Data Index: 4467224 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7564. Min Range: -10.7564
Max Act: 9.6314. Min Act: -0.1700
Data Index: 5588744 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7564. Min Range: -10.7564
Max Act: 9.6314. Min Act: -0.1700
Data Index: 3333319 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7564. Min Range: -10.7564
Max Act: 9.6314. Min Act: -0.1700
Data Index: 5238711 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7564. Min Range: -10.7564
Max Act: 9.6314. Min Act: -0.1700
Data Index: 2990084 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7564. Min Range: -10.7564
Max Act: 9.5689. Min Act: -0.1700
Data Index: 4531111 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7564. Min Range: -10.7564
Max Act: 9.5064. Min Act: -0.1700
Data Index: 2829214 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19