Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3221 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0587. Min Range: -6.0587
Max Act: 6.0587. Min Act: -0.1700
Data Index: 7056751 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0587. Min Range: -6.0587
Max Act: 5.9962. Min Act: -0.1700
Data Index: 342665 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0587. Min Range: -6.0587
Max Act: 5.9337. Min Act: -0.1700
Data Index: 4666352 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0587. Min Range: -6.0587
Max Act: 5.9024. Min Act: -0.1700
Data Index: 5904613 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0587. Min Range: -6.0587
Max Act: 5.8712. Min Act: -0.1700
Data Index: 567390 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0587. Min Range: -6.0587
Max Act: 5.8712. Min Act: -0.1700
Data Index: 5268752 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0587. Min Range: -6.0587
Max Act: 5.8712. Min Act: -0.1700
Data Index: 6592386 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0587. Min Range: -6.0587
Max Act: 5.8399. Min Act: -0.1700
Data Index: 1558803 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0587. Min Range: -6.0587
Max Act: 5.8399. Min Act: -0.1700
Data Index: 2235999 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0587. Min Range: -6.0587
Max Act: 5.8399. Min Act: -0.1700
Data Index: 6631030 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0587. Min Range: -6.0587
Max Act: 5.8399. Min Act: -0.1700
Data Index: 3966250 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0587. Min Range: -6.0587
Max Act: 5.8399. Min Act: -0.1700
Data Index: 634657 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0587. Min Range: -6.0587
Max Act: 5.8399. Min Act: -0.1700
Data Index: 6980569 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0587. Min Range: -6.0587
Max Act: 5.8399. Min Act: -0.1700
Data Index: 7863510 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0587. Min Range: -6.0587
Max Act: 5.8399. Min Act: -0.1700
Data Index: 1089138 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0587. Min Range: -6.0587
Max Act: 5.8087. Min Act: -0.1700
Data Index: 1505673 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0587. Min Range: -6.0587
Max Act: 5.8087. Min Act: -0.1700
Data Index: 3042703 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0587. Min Range: -6.0587
Max Act: 5.8087. Min Act: -0.1700
Data Index: 277922 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0587. Min Range: -6.0587
Max Act: 5.8087. Min Act: -0.1700
Data Index: 5489577 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0587. Min Range: -6.0587
Max Act: 5.8087. Min Act: -0.1700
Data Index: 3912100 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #19