Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5063 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6918. Min Range: -2.6918
Max Act: 2.6918. Min Act: -0.1700
Data Index: 980537 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6918. Min Range: -2.6918
Max Act: 2.6116. Min Act: -0.1700
Data Index: 532837 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6918. Min Range: -2.6918
Max Act: 2.5794. Min Act: -0.1700
Data Index: 7652288 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6918. Min Range: -2.6918
Max Act: 2.5471. Min Act: -0.1700
Data Index: 7843338 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6918. Min Range: -2.6918
Max Act: 2.5310. Min Act: -0.1700
Data Index: 532831 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6918. Min Range: -2.6918
Max Act: 2.4824. Min Act: -0.1700
Data Index: 441890 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6918. Min Range: -2.6918
Max Act: 2.4986. Min Act: -0.1700
Data Index: 6039094 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6918. Min Range: -2.6918
Max Act: 2.4661. Min Act: -0.1700
Data Index: 5223681 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6918. Min Range: -2.6918
Max Act: 2.4824. Min Act: -0.1700
Data Index: 6226190 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6918. Min Range: -2.6918
Max Act: 2.4661. Min Act: -0.1700
Data Index: 1000660 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6918. Min Range: -2.6918
Max Act: 2.4661. Min Act: -0.1700
Data Index: 8495449 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6918. Min Range: -2.6918
Max Act: 2.4499. Min Act: -0.1700
Data Index: 4515651 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6918. Min Range: -2.6918
Max Act: 2.4499. Min Act: -0.1700
Data Index: 2975163 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6918. Min Range: -2.6918
Max Act: 2.4661. Min Act: -0.1700
Data Index: 3786673 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6918. Min Range: -2.6918
Max Act: 2.4499. Min Act: -0.1700
Data Index: 2507028 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6918. Min Range: -2.6918
Max Act: 2.4336. Min Act: -0.1700
Data Index: 7385332 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6918. Min Range: -2.6918
Max Act: 2.4173. Min Act: -0.1700
Data Index: 7434757 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6918. Min Range: -2.6918
Max Act: 2.4173. Min Act: -0.1700
Data Index: 3716108 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6918. Min Range: -2.6918
Max Act: 2.4173. Min Act: -0.1700
Data Index: 4462976 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6918. Min Range: -2.6918
Max Act: 2.4173. Min Act: -0.1700
Data Index: 6809419 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19