Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1778 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7152. Min Range: -4.7152
Max Act: 4.7152. Min Act: -0.1700
Data Index: 6975068 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7152. Min Range: -4.7152
Max Act: 4.7152. Min Act: -0.1700
Data Index: 3500864 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7152. Min Range: -4.7152
Max Act: 4.5902. Min Act: -0.1700
Data Index: 1434574 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7152. Min Range: -4.7152
Max Act: 4.5902. Min Act: -0.1700
Data Index: 824203 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7152. Min Range: -4.7152
Max Act: 4.5589. Min Act: -0.1700
Data Index: 4449687 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7152. Min Range: -4.7152
Max Act: 4.5277. Min Act: -0.1700
Data Index: 4528625 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7152. Min Range: -4.7152
Max Act: 4.5277. Min Act: -0.1700
Data Index: 385485 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7152. Min Range: -4.7152
Max Act: 4.5589. Min Act: -0.1700
Data Index: 2507847 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7152. Min Range: -4.7152
Max Act: 4.5277. Min Act: -0.1700
Data Index: 6599303 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7152. Min Range: -4.7152
Max Act: 4.4964. Min Act: -0.1700
Data Index: 6631074 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7152. Min Range: -4.7152
Max Act: 4.5277. Min Act: -0.1700
Data Index: 4965454 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7152. Min Range: -4.7152
Max Act: 4.5277. Min Act: -0.1700
Data Index: 3890103 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7152. Min Range: -4.7152
Max Act: 4.4964. Min Act: -0.1700
Data Index: 2494760 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7152. Min Range: -4.7152
Max Act: 4.4652. Min Act: -0.1700
Data Index: 1114527 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7152. Min Range: -4.7152
Max Act: 4.4652. Min Act: -0.1700
Data Index: 5119109 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7152. Min Range: -4.7152
Max Act: 4.4339. Min Act: -0.1700
Data Index: 5919725 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7152. Min Range: -4.7152
Max Act: 4.4339. Min Act: -0.1700
Data Index: 3618890 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7152. Min Range: -4.7152
Max Act: 4.4339. Min Act: -0.1700
Data Index: 443327 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7152. Min Range: -4.7152
Max Act: 4.4339. Min Act: -0.1700
Data Index: 806889 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7152. Min Range: -4.7152
Max Act: 4.4339. Min Act: -0.1700
Data Index: 6386175 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19