Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3055 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6525. Min Range: -6.6525
Max Act: 6.6525. Min Act: -0.1700
Data Index: 1483612 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6525. Min Range: -6.6525
Max Act: 6.3400. Min Act: -0.1700
Data Index: 3332846 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6525. Min Range: -6.6525
Max Act: 6.2462. Min Act: -0.1700
Data Index: 1900364 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6525. Min Range: -6.6525
Max Act: 6.1837. Min Act: -0.1700
Data Index: 6543088 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6525. Min Range: -6.6525
Max Act: 6.0587. Min Act: -0.1700
Data Index: 8234522 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6525. Min Range: -6.6525
Max Act: 6.0587. Min Act: -0.1700
Data Index: 3951170 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6525. Min Range: -6.6525
Max Act: 6.0587. Min Act: -0.1700
Data Index: 3291020 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6525. Min Range: -6.6525
Max Act: 6.0275. Min Act: -0.1700
Data Index: 6000885 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6525. Min Range: -6.6525
Max Act: 6.0587. Min Act: -0.1700
Data Index: 1132 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6525. Min Range: -6.6525
Max Act: 6.0587. Min Act: -0.1700
Data Index: 8394458 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6525. Min Range: -6.6525
Max Act: 5.9962. Min Act: -0.1700
Data Index: 8672291 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6525. Min Range: -6.6525
Max Act: 5.9962. Min Act: -0.1700
Data Index: 6657379 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6525. Min Range: -6.6525
Max Act: 5.9650. Min Act: -0.1700
Data Index: 6000884 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6525. Min Range: -6.6525
Max Act: 5.9650. Min Act: -0.1700
Data Index: 545491 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6525. Min Range: -6.6525
Max Act: 5.9650. Min Act: -0.1700
Data Index: 3252341 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6525. Min Range: -6.6525
Max Act: 5.9337. Min Act: -0.1700
Data Index: 88739 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6525. Min Range: -6.6525
Max Act: 5.9337. Min Act: -0.1700
Data Index: 8435079 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6525. Min Range: -6.6525
Max Act: 5.9337. Min Act: -0.1700
Data Index: 5170618 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6525. Min Range: -6.6525
Max Act: 5.9025. Min Act: -0.1700
Data Index: 6249266 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6525. Min Range: -6.6525
Max Act: 5.9337. Min Act: -0.1700
Data Index: 545490 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #19