Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6090 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.9030. Min Act: -0.1700
Data Index: 7110303 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.7155. Min Act: -0.1700
Data Index: 981373 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.5280. Min Act: -0.1700
Data Index: 1842265 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.4968. Min Act: -0.1700
Data Index: 8425021 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.4968. Min Act: -0.1700
Data Index: 1616156 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.4030. Min Act: -0.1700
Data Index: 783827 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.3718. Min Act: -0.1700
Data Index: 2894441 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.3093. Min Act: -0.1700
Data Index: 6907212 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.3405. Min Act: -0.1700
Data Index: 8389280 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.3093. Min Act: -0.1700
Data Index: 2929552 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.3093. Min Act: -0.1700
Data Index: 5553529 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.3093. Min Act: -0.1700
Data Index: 124835 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.3405. Min Act: -0.1700
Data Index: 5873050 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.3093. Min Act: -0.1700
Data Index: 8554194 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.2780. Min Act: -0.1700
Data Index: 8587329 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.3093. Min Act: -0.1700
Data Index: 144157 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.2468. Min Act: -0.1700
Data Index: 3694896 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.2468. Min Act: -0.1700
Data Index: 6828457 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.2155. Min Act: -0.1700
Data Index: 4593562 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.2468. Min Act: -0.1700
Data Index: 3488166 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19