Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4298 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.2562. Min Range: -11.2562
Max Act: 11.2562. Min Act: -0.1700
Data Index: 2766258 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.2562. Min Range: -11.2562
Max Act: 11.1937. Min Act: -0.1700
Data Index: 5712242 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.2562. Min Range: -11.2562
Max Act: 11.1937. Min Act: -0.1700
Data Index: 476143 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.2562. Min Range: -11.2562
Max Act: 11.1312. Min Act: -0.1700
Data Index: 7580661 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.2562. Min Range: -11.2562
Max Act: 11.1312. Min Act: -0.1700
Data Index: 4122693 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.2562. Min Range: -11.2562
Max Act: 11.0062. Min Act: -0.1700
Data Index: 6660954 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.2562. Min Range: -11.2562
Max Act: 11.0687. Min Act: -0.1700
Data Index: 6422749 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.2562. Min Range: -11.2562
Max Act: 10.8812. Min Act: -0.1700
Data Index: 1997344 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.2562. Min Range: -11.2562
Max Act: 10.8187. Min Act: -0.1700
Data Index: 4624852 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.2562. Min Range: -11.2562
Max Act: 10.7562. Min Act: -0.1700
Data Index: 8665422 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.2562. Min Range: -11.2562
Max Act: 10.7562. Min Act: -0.1700
Data Index: 1642667 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.2562. Min Range: -11.2562
Max Act: 10.6937. Min Act: -0.1700
Data Index: 1656999 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.2562. Min Range: -11.2562
Max Act: 10.6312. Min Act: -0.1700
Data Index: 237062 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.2562. Min Range: -11.2562
Max Act: 10.6312. Min Act: -0.1700
Data Index: 1802773 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.2562. Min Range: -11.2562
Max Act: 10.6937. Min Act: -0.1700
Data Index: 7198246 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.2562. Min Range: -11.2562
Max Act: 10.6312. Min Act: -0.1700
Data Index: 981432 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.2562. Min Range: -11.2562
Max Act: 10.6312. Min Act: -0.1700
Data Index: 341180 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.2562. Min Range: -11.2562
Max Act: 10.6937. Min Act: -0.1700
Data Index: 739113 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.2562. Min Range: -11.2562
Max Act: 10.6312. Min Act: -0.1700
Data Index: 7138143 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.2562. Min Range: -11.2562
Max Act: 10.5687. Min Act: -0.1700
Data Index: 3212092 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #19