Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4971 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1287. Min Range: -5.1287
Max Act: 5.1287. Min Act: -0.1700
Data Index: 6494900 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1287. Min Range: -5.1287
Max Act: 5.0037. Min Act: -0.1700
Data Index: 1570910 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1287. Min Range: -5.1287
Max Act: 4.9724. Min Act: -0.1700
Data Index: 2911458 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1287. Min Range: -5.1287
Max Act: 4.9099. Min Act: -0.1700
Data Index: 3012344 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1287. Min Range: -5.1287
Max Act: 4.9099. Min Act: -0.1700
Data Index: 4207930 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1287. Min Range: -5.1287
Max Act: 4.8474. Min Act: -0.1700
Data Index: 2360303 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1287. Min Range: -5.1287
Max Act: 4.8787. Min Act: -0.1700
Data Index: 8091718 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1287. Min Range: -5.1287
Max Act: 4.8162. Min Act: -0.1700
Data Index: 8492985 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1287. Min Range: -5.1287
Max Act: 4.7849. Min Act: -0.1700
Data Index: 461322 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1287. Min Range: -5.1287
Max Act: 4.8162. Min Act: -0.1700
Data Index: 665193 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1287. Min Range: -5.1287
Max Act: 4.7537. Min Act: -0.1700
Data Index: 8129711 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1287. Min Range: -5.1287
Max Act: 4.7537. Min Act: -0.1700
Data Index: 7083226 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1287. Min Range: -5.1287
Max Act: 4.7537. Min Act: -0.1700
Data Index: 5219131 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1287. Min Range: -5.1287
Max Act: 4.7224. Min Act: -0.1700
Data Index: 7132006 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1287. Min Range: -5.1287
Max Act: 4.7224. Min Act: -0.1700
Data Index: 709023 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1287. Min Range: -5.1287
Max Act: 4.7224. Min Act: -0.1700
Data Index: 5918890 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1287. Min Range: -5.1287
Max Act: 4.7224. Min Act: -0.1700
Data Index: 7007252 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1287. Min Range: -5.1287
Max Act: 4.6599. Min Act: -0.1700
Data Index: 4840031 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1287. Min Range: -5.1287
Max Act: 4.6912. Min Act: -0.1700
Data Index: 389004 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1287. Min Range: -5.1287
Max Act: 4.6912. Min Act: -0.1700
Data Index: 6522142 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19