Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3600 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2912. Min Range: -6.2912
Max Act: 6.2912. Min Act: -0.1694
Data Index: 367270 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2912. Min Range: -6.2912
Max Act: 6.1974. Min Act: -0.1700
Data Index: 6262130 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2912. Min Range: -6.2912
Max Act: 6.1349. Min Act: -0.1700
Data Index: 1305785 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2912. Min Range: -6.2912
Max Act: 6.0724. Min Act: -0.1700
Data Index: 3035442 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2912. Min Range: -6.2912
Max Act: 5.8849. Min Act: -0.0076
Data Index: 2588389 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2912. Min Range: -6.2912
Max Act: 5.8849. Min Act: -0.1543
Data Index: 2588397 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2912. Min Range: -6.2912
Max Act: 5.8537. Min Act: -0.1700
Data Index: 7869427 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2912. Min Range: -6.2912
Max Act: 5.8537. Min Act: -0.1700
Data Index: 7001336 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2912. Min Range: -6.2912
Max Act: 5.8537. Min Act: -0.1700
Data Index: 5854067 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2912. Min Range: -6.2912
Max Act: 5.8537. Min Act: -0.1700
Data Index: 5785445 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2912. Min Range: -6.2912
Max Act: 5.8537. Min Act: -0.1700
Data Index: 3509188 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2912. Min Range: -6.2912
Max Act: 5.8224. Min Act: -0.1668
Data Index: 4179847 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2912. Min Range: -6.2912
Max Act: 5.7912. Min Act: -0.1700
Data Index: 4548621 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2912. Min Range: -6.2912
Max Act: 5.7912. Min Act: -0.1699
Data Index: 7827339 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2912. Min Range: -6.2912
Max Act: 5.7912. Min Act: -0.1700
Data Index: 4919846 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2912. Min Range: -6.2912
Max Act: 5.7912. Min Act: -0.1423
Data Index: 2220248 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2912. Min Range: -6.2912
Max Act: 5.7912. Min Act: -0.1697
Data Index: 2588401 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2912. Min Range: -6.2912
Max Act: 5.7912. Min Act: -0.0216
Data Index: 6852818 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2912. Min Range: -6.2912
Max Act: 5.7599. Min Act: -0.1423
Data Index: 4179846 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2912. Min Range: -6.2912
Max Act: 5.7599. Min Act: -0.1690
Data Index: 377336 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19