Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2957 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1131. Min Range: -5.1131
Max Act: 5.1131. Min Act: -0.1700
Data Index: 7895890 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1131. Min Range: -5.1131
Max Act: 4.9881. Min Act: -0.1700
Data Index: 3105164 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1131. Min Range: -5.1131
Max Act: 4.9881. Min Act: -0.1700
Data Index: 2805469 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1131. Min Range: -5.1131
Max Act: 4.8944. Min Act: -0.1700
Data Index: 7993837 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1131. Min Range: -5.1131
Max Act: 4.8944. Min Act: -0.1699
Data Index: 1347139 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1131. Min Range: -5.1131
Max Act: 4.8631. Min Act: -0.1700
Data Index: 5746896 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1131. Min Range: -5.1131
Max Act: 4.8006. Min Act: -0.1700
Data Index: 6989029 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1131. Min Range: -5.1131
Max Act: 4.7694. Min Act: -0.1700
Data Index: 8740608 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1131. Min Range: -5.1131
Max Act: 4.7381. Min Act: -0.1700
Data Index: 3441561 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1131. Min Range: -5.1131
Max Act: 4.7694. Min Act: -0.1700
Data Index: 7476390 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1131. Min Range: -5.1131
Max Act: 4.7694. Min Act: -0.1700
Data Index: 4790536 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1131. Min Range: -5.1131
Max Act: 4.7694. Min Act: -0.1700
Data Index: 3122760 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1131. Min Range: -5.1131
Max Act: 4.7381. Min Act: -0.1700
Data Index: 3121793 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1131. Min Range: -5.1131
Max Act: 4.7381. Min Act: -0.1700
Data Index: 2405368 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1131. Min Range: -5.1131
Max Act: 4.7069. Min Act: -0.1700
Data Index: 857183 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1131. Min Range: -5.1131
Max Act: 4.7069. Min Act: -0.1700
Data Index: 5882078 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1131. Min Range: -5.1131
Max Act: 4.7069. Min Act: -0.1700
Data Index: 570094 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1131. Min Range: -5.1131
Max Act: 4.7069. Min Act: -0.1700
Data Index: 918132 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1131. Min Range: -5.1131
Max Act: 4.7069. Min Act: -0.1700
Data Index: 1825920 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1131. Min Range: -5.1131
Max Act: 4.6756. Min Act: -0.1700
Data Index: 8491391 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #19