Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 750 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8887. Min Range: -5.8887
Max Act: 5.8887. Min Act: -0.1700
Data Index: 2627711 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8887. Min Range: -5.8887
Max Act: 5.8262. Min Act: -0.1700
Data Index: 5841423 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8887. Min Range: -5.8887
Max Act: 5.8262. Min Act: -0.1700
Data Index: 999958 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8887. Min Range: -5.8887
Max Act: 5.7637. Min Act: -0.1700
Data Index: 2872102 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8887. Min Range: -5.8887
Max Act: 5.7637. Min Act: -0.1700
Data Index: 5851337 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8887. Min Range: -5.8887
Max Act: 5.7950. Min Act: -0.1700
Data Index: 3327267 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8887. Min Range: -5.8887
Max Act: 5.7325. Min Act: -0.1700
Data Index: 328669 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8887. Min Range: -5.8887
Max Act: 5.6700. Min Act: -0.1700
Data Index: 35614 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8887. Min Range: -5.8887
Max Act: 5.6700. Min Act: -0.1700
Data Index: 5140203 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8887. Min Range: -5.8887
Max Act: 5.6387. Min Act: -0.1700
Data Index: 1294583 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8887. Min Range: -5.8887
Max Act: 5.6075. Min Act: -0.1700
Data Index: 4082299 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8887. Min Range: -5.8887
Max Act: 5.6075. Min Act: -0.1700
Data Index: 7864270 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8887. Min Range: -5.8887
Max Act: 5.6387. Min Act: -0.1700
Data Index: 8150802 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8887. Min Range: -5.8887
Max Act: 5.6075. Min Act: -0.1700
Data Index: 1024413 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8887. Min Range: -5.8887
Max Act: 5.5137. Min Act: -0.1700
Data Index: 7903098 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8887. Min Range: -5.8887
Max Act: 5.5137. Min Act: -0.1700
Data Index: 8200082 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8887. Min Range: -5.8887
Max Act: 5.4512. Min Act: -0.1700
Data Index: 5404335 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8887. Min Range: -5.8887
Max Act: 5.4825. Min Act: -0.1700
Data Index: 4016698 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8887. Min Range: -5.8887
Max Act: 5.4825. Min Act: -0.1700
Data Index: 1256030 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8887. Min Range: -5.8887
Max Act: 5.4825. Min Act: -0.1700
Data Index: 1617509 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19