Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 33 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2071. Min Range: -6.2071
Max Act: 6.2071. Min Act: -0.1700
Data Index: 2469205 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2071. Min Range: -6.2071
Max Act: 6.0196. Min Act: -0.1700
Data Index: 7822460 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2071. Min Range: -6.2071
Max Act: 5.9571. Min Act: -0.1700
Data Index: 1160586 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2071. Min Range: -6.2071
Max Act: 5.9259. Min Act: -0.1700
Data Index: 8561139 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2071. Min Range: -6.2071
Max Act: 5.8634. Min Act: -0.1700
Data Index: 817108 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2071. Min Range: -6.2071
Max Act: 5.8946. Min Act: -0.1700
Data Index: 3362652 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2071. Min Range: -6.2071
Max Act: 5.8946. Min Act: -0.1700
Data Index: 3747298 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2071. Min Range: -6.2071
Max Act: 5.8634. Min Act: -0.1700
Data Index: 7511671 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2071. Min Range: -6.2071
Max Act: 5.8946. Min Act: -0.1700
Data Index: 6064711 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2071. Min Range: -6.2071
Max Act: 5.8634. Min Act: -0.1700
Data Index: 1160585 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2071. Min Range: -6.2071
Max Act: 5.8634. Min Act: -0.1700
Data Index: 3104764 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2071. Min Range: -6.2071
Max Act: 5.8321. Min Act: -0.1700
Data Index: 7294020 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2071. Min Range: -6.2071
Max Act: 5.8009. Min Act: -0.1700
Data Index: 797559 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2071. Min Range: -6.2071
Max Act: 5.8009. Min Act: -0.1700
Data Index: 8167956 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2071. Min Range: -6.2071
Max Act: 5.7384. Min Act: -0.1700
Data Index: 3662988 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2071. Min Range: -6.2071
Max Act: 5.7384. Min Act: -0.1700
Data Index: 1479024 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2071. Min Range: -6.2071
Max Act: 5.7384. Min Act: -0.1700
Data Index: 6318422 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2071. Min Range: -6.2071
Max Act: 5.7071. Min Act: -0.1700
Data Index: 341071 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2071. Min Range: -6.2071
Max Act: 5.7071. Min Act: -0.1700
Data Index: 2280617 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2071. Min Range: -6.2071
Max Act: 5.7071. Min Act: -0.1700
Data Index: 5551920 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19