Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3917 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2968. Min Range: -5.2968
Max Act: 5.2968. Min Act: -0.1700
Data Index: 7954221 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2968. Min Range: -5.2968
Max Act: 5.2655. Min Act: -0.1700
Data Index: 8402697 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2968. Min Range: -5.2968
Max Act: 5.2655. Min Act: -0.1700
Data Index: 3350651 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2968. Min Range: -5.2968
Max Act: 5.2655. Min Act: -0.1700
Data Index: 3065545 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2968. Min Range: -5.2968
Max Act: 5.2343. Min Act: -0.1700
Data Index: 7759629 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2968. Min Range: -5.2968
Max Act: 5.2343. Min Act: -0.1700
Data Index: 1716210 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2968. Min Range: -5.2968
Max Act: 5.2030. Min Act: -0.1700
Data Index: 4276820 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2968. Min Range: -5.2968
Max Act: 5.2030. Min Act: -0.1700
Data Index: 807459 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2968. Min Range: -5.2968
Max Act: 5.2030. Min Act: -0.1700
Data Index: 3547497 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2968. Min Range: -5.2968
Max Act: 5.1718. Min Act: -0.1700
Data Index: 360161 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2968. Min Range: -5.2968
Max Act: 5.1093. Min Act: -0.1700
Data Index: 1247287 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2968. Min Range: -5.2968
Max Act: 5.1718. Min Act: -0.1700
Data Index: 600863 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2968. Min Range: -5.2968
Max Act: 5.1405. Min Act: -0.1700
Data Index: 7661116 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2968. Min Range: -5.2968
Max Act: 5.1093. Min Act: -0.1700
Data Index: 2522989 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2968. Min Range: -5.2968
Max Act: 5.1093. Min Act: -0.1700
Data Index: 71456 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2968. Min Range: -5.2968
Max Act: 5.1093. Min Act: -0.1700
Data Index: 4811459 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2968. Min Range: -5.2968
Max Act: 5.1093. Min Act: -0.1700
Data Index: 982899 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2968. Min Range: -5.2968
Max Act: 5.1093. Min Act: -0.1700
Data Index: 6021382 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2968. Min Range: -5.2968
Max Act: 5.1093. Min Act: -0.1700
Data Index: 7568656 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2968. Min Range: -5.2968
Max Act: 5.0780. Min Act: -0.1700
Data Index: 137933 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #19