Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 380 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8259. Min Range: -6.8259
Max Act: 6.8259. Min Act: -0.1700
Data Index: 4671197 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8259. Min Range: -6.8259
Max Act: 6.4197. Min Act: -0.1700
Data Index: 2581059 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8259. Min Range: -6.8259
Max Act: 6.2947. Min Act: -0.1700
Data Index: 1512211 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8259. Min Range: -6.8259
Max Act: 6.2634. Min Act: -0.1700
Data Index: 4422289 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8259. Min Range: -6.8259
Max Act: 6.2634. Min Act: -0.1700
Data Index: 5741880 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8259. Min Range: -6.8259
Max Act: 6.2634. Min Act: -0.1700
Data Index: 2376225 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8259. Min Range: -6.8259
Max Act: 6.2322. Min Act: -0.1700
Data Index: 7664833 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8259. Min Range: -6.8259
Max Act: 6.2322. Min Act: -0.1700
Data Index: 951095 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8259. Min Range: -6.8259
Max Act: 6.1697. Min Act: -0.1700
Data Index: 8282491 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8259. Min Range: -6.8259
Max Act: 6.1384. Min Act: -0.1700
Data Index: 4449298 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8259. Min Range: -6.8259
Max Act: 6.1384. Min Act: -0.1700
Data Index: 3987882 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8259. Min Range: -6.8259
Max Act: 6.1384. Min Act: -0.1700
Data Index: 3111058 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8259. Min Range: -6.8259
Max Act: 6.1384. Min Act: -0.1700
Data Index: 8650619 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8259. Min Range: -6.8259
Max Act: 6.1072. Min Act: -0.1700
Data Index: 4537524 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8259. Min Range: -6.8259
Max Act: 6.1384. Min Act: -0.1700
Data Index: 2830485 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8259. Min Range: -6.8259
Max Act: 6.0759. Min Act: -0.1700
Data Index: 2948418 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8259. Min Range: -6.8259
Max Act: 6.0759. Min Act: -0.1700
Data Index: 6504411 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8259. Min Range: -6.8259
Max Act: 6.0759. Min Act: -0.1700
Data Index: 4832887 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8259. Min Range: -6.8259
Max Act: 6.0759. Min Act: -0.1700
Data Index: 3721119 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8259. Min Range: -6.8259
Max Act: 6.0447. Min Act: -0.1700
Data Index: 6584968 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19