Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3368 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1743. Min Range: -3.1743
Max Act: 3.1743. Min Act: -0.1700
Data Index: 30328 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1743. Min Range: -3.1743
Max Act: 3.1585. Min Act: -0.1700
Data Index: 3386883 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1743. Min Range: -3.1743
Max Act: 3.1271. Min Act: -0.1700
Data Index: 5077612 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1743. Min Range: -3.1743
Max Act: 3.1271. Min Act: -0.1700
Data Index: 2507226 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1743. Min Range: -3.1743
Max Act: 3.0640. Min Act: -0.1700
Data Index: 5803587 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1743. Min Range: -3.1743
Max Act: 3.0482. Min Act: -0.1700
Data Index: 3936687 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1743. Min Range: -3.1743
Max Act: 3.0482. Min Act: -0.1700
Data Index: 3201204 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1743. Min Range: -3.1743
Max Act: 3.0482. Min Act: -0.1700
Data Index: 5821690 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1743. Min Range: -3.1743
Max Act: 3.0324. Min Act: -0.1700
Data Index: 8204652 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1743. Min Range: -3.1743
Max Act: 3.0324. Min Act: -0.1700
Data Index: 4929592 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1743. Min Range: -3.1743
Max Act: 3.0324. Min Act: -0.1700
Data Index: 1286377 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1743. Min Range: -3.1743
Max Act: 3.0324. Min Act: -0.1700
Data Index: 3171978 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1743. Min Range: -3.1743
Max Act: 3.0167. Min Act: -0.1700
Data Index: 4063912 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1743. Min Range: -3.1743
Max Act: 3.0167. Min Act: -0.1700
Data Index: 2137007 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1743. Min Range: -3.1743
Max Act: 3.0167. Min Act: -0.1700
Data Index: 286538 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1743. Min Range: -3.1743
Max Act: 2.9850. Min Act: -0.1700
Data Index: 4929301 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1743. Min Range: -3.1743
Max Act: 3.0009. Min Act: -0.1700
Data Index: 1976320 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1743. Min Range: -3.1743
Max Act: 3.0009. Min Act: -0.1700
Data Index: 6253453 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1743. Min Range: -3.1743
Max Act: 3.0009. Min Act: -0.1700
Data Index: 6752622 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1743. Min Range: -3.1743
Max Act: 3.0009. Min Act: -0.1700
Data Index: 5812153 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19