Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 545 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1217. Min Range: -6.1217
Max Act: 6.1217. Min Act: -0.1700
Data Index: 6414219 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1217. Min Range: -6.1217
Max Act: 6.0905. Min Act: -0.1700
Data Index: 7127842 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1217. Min Range: -6.1217
Max Act: 6.0592. Min Act: -0.1700
Data Index: 77559 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1217. Min Range: -6.1217
Max Act: 6.0280. Min Act: -0.1700
Data Index: 6528718 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1217. Min Range: -6.1217
Max Act: 5.9655. Min Act: -0.1700
Data Index: 46838 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1217. Min Range: -6.1217
Max Act: 5.9342. Min Act: -0.1700
Data Index: 5725802 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1217. Min Range: -6.1217
Max Act: 5.8717. Min Act: -0.1700
Data Index: 8832667 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1217. Min Range: -6.1217
Max Act: 5.8717. Min Act: -0.1700
Data Index: 1754379 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1217. Min Range: -6.1217
Max Act: 5.8405. Min Act: -0.1700
Data Index: 769912 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1217. Min Range: -6.1217
Max Act: 5.7467. Min Act: -0.1700
Data Index: 854471 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1217. Min Range: -6.1217
Max Act: 5.6842. Min Act: -0.1700
Data Index: 7725179 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1217. Min Range: -6.1217
Max Act: 5.6842. Min Act: -0.1700
Data Index: 5592937 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1217. Min Range: -6.1217
Max Act: 5.6530. Min Act: -0.1700
Data Index: 1163474 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1217. Min Range: -6.1217
Max Act: 5.6530. Min Act: -0.1700
Data Index: 7504781 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1217. Min Range: -6.1217
Max Act: 5.6217. Min Act: -0.1700
Data Index: 265019 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1217. Min Range: -6.1217
Max Act: 5.6530. Min Act: -0.1700
Data Index: 3733601 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1217. Min Range: -6.1217
Max Act: 5.5905. Min Act: -0.1700
Data Index: 4810876 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1217. Min Range: -6.1217
Max Act: 5.6217. Min Act: -0.1700
Data Index: 6264296 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1217. Min Range: -6.1217
Max Act: 5.6217. Min Act: -0.1700
Data Index: 7457416 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1217. Min Range: -6.1217
Max Act: 5.6217. Min Act: -0.1700
Data Index: 762725 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #19