Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1964 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0783. Min Range: -8.0783
Max Act: 8.0783. Min Act: -0.1700
Data Index: 2667376 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0783. Min Range: -8.0783
Max Act: 7.4220. Min Act: -0.1700
Data Index: 4568012 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0783. Min Range: -8.0783
Max Act: 7.2345. Min Act: -0.1700
Data Index: 757203 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0783. Min Range: -8.0783
Max Act: 7.0470. Min Act: -0.1700
Data Index: 3269415 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0783. Min Range: -8.0783
Max Act: 7.0470. Min Act: -0.1700
Data Index: 813850 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0783. Min Range: -8.0783
Max Act: 7.0470. Min Act: -0.1700
Data Index: 5583216 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0783. Min Range: -8.0783
Max Act: 7.0158. Min Act: -0.1700
Data Index: 176933 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0783. Min Range: -8.0783
Max Act: 6.9533. Min Act: -0.1700
Data Index: 1504752 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0783. Min Range: -8.0783
Max Act: 6.9220. Min Act: -0.1700
Data Index: 849329 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0783. Min Range: -8.0783
Max Act: 6.8908. Min Act: -0.1700
Data Index: 400084 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0783. Min Range: -8.0783
Max Act: 6.9220. Min Act: -0.1700
Data Index: 6046483 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0783. Min Range: -8.0783
Max Act: 6.8908. Min Act: -0.1700
Data Index: 7708960 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0783. Min Range: -8.0783
Max Act: 6.8283. Min Act: -0.1700
Data Index: 2764025 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0783. Min Range: -8.0783
Max Act: 6.8595. Min Act: -0.1700
Data Index: 1796696 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0783. Min Range: -8.0783
Max Act: 6.8283. Min Act: -0.1700
Data Index: 420732 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0783. Min Range: -8.0783
Max Act: 6.7658. Min Act: -0.1700
Data Index: 2775732 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0783. Min Range: -8.0783
Max Act: 6.7658. Min Act: -0.1700
Data Index: 1503639 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0783. Min Range: -8.0783
Max Act: 6.7658. Min Act: -0.1700
Data Index: 6146604 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0783. Min Range: -8.0783
Max Act: 6.7345. Min Act: -0.1700
Data Index: 1503624 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0783. Min Range: -8.0783
Max Act: 6.7658. Min Act: -0.1700
Data Index: 1630436 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19