Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3778 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5985. Min Range: -5.5985
Max Act: 5.5985. Min Act: -0.1700
Data Index: 7086535 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5985. Min Range: -5.5985
Max Act: 5.5048. Min Act: -0.1700
Data Index: 5595979 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5985. Min Range: -5.5985
Max Act: 5.4735. Min Act: -0.1700
Data Index: 1504105 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5985. Min Range: -5.5985
Max Act: 5.4735. Min Act: -0.1700
Data Index: 632262 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5985. Min Range: -5.5985
Max Act: 5.4423. Min Act: -0.1700
Data Index: 7118445 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5985. Min Range: -5.5985
Max Act: 5.4110. Min Act: -0.1700
Data Index: 894882 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5985. Min Range: -5.5985
Max Act: 5.4423. Min Act: -0.1700
Data Index: 5578693 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5985. Min Range: -5.5985
Max Act: 5.4423. Min Act: -0.1700
Data Index: 5126344 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5985. Min Range: -5.5985
Max Act: 5.4423. Min Act: -0.1700
Data Index: 2718656 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5985. Min Range: -5.5985
Max Act: 5.4110. Min Act: -0.1700
Data Index: 3661848 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5985. Min Range: -5.5985
Max Act: 5.3798. Min Act: -0.1700
Data Index: 5234085 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5985. Min Range: -5.5985
Max Act: 5.3798. Min Act: -0.1700
Data Index: 905331 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5985. Min Range: -5.5985
Max Act: 5.3798. Min Act: -0.1700
Data Index: 6490827 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5985. Min Range: -5.5985
Max Act: 5.3798. Min Act: -0.1700
Data Index: 1515455 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5985. Min Range: -5.5985
Max Act: 5.3798. Min Act: -0.1700
Data Index: 1117438 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5985. Min Range: -5.5985
Max Act: 5.4110. Min Act: -0.1700
Data Index: 4460699 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5985. Min Range: -5.5985
Max Act: 5.3798. Min Act: -0.1700
Data Index: 1621163 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5985. Min Range: -5.5985
Max Act: 5.3485. Min Act: -0.1700
Data Index: 5654124 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5985. Min Range: -5.5985
Max Act: 5.3173. Min Act: -0.1700
Data Index: 74704 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5985. Min Range: -5.5985
Max Act: 5.3798. Min Act: -0.1700
Data Index: 18997 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19