Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5344 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.9619. Min Act: -0.1700
Data Index: 5840758 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.7744. Min Act: -0.1700
Data Index: 321416 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.8056. Min Act: -0.1700
Data Index: 5840759 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.7431. Min Act: -0.1700
Data Index: 213472 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.7119. Min Act: -0.1700
Data Index: 5027121 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.7119. Min Act: -0.1700
Data Index: 343956 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.6806. Min Act: -0.1700
Data Index: 7389060 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.6806. Min Act: -0.1700
Data Index: 1715772 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.6806. Min Act: -0.1700
Data Index: 6475463 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.6181. Min Act: -0.1700
Data Index: 5840756 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.6181. Min Act: -0.1700
Data Index: 6582614 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.6181. Min Act: -0.1700
Data Index: 340793 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.6494. Min Act: -0.1700
Data Index: 1989432 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.5869. Min Act: -0.1700
Data Index: 3848993 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.5869. Min Act: -0.1700
Data Index: 3773366 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.5869. Min Act: -0.1700
Data Index: 6505841 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.5869. Min Act: -0.1700
Data Index: 353862 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.5869. Min Act: -0.1700
Data Index: 4162746 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.5869. Min Act: -0.1700
Data Index: 488917 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.5869. Min Act: -0.1700
Data Index: 5692618 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19