Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3265 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1803. Min Range: -6.1803
Max Act: 6.1803. Min Act: -0.1700
Data Index: 6811203 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1803. Min Range: -6.1803
Max Act: 5.9616. Min Act: -0.1700
Data Index: 6805416 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1803. Min Range: -6.1803
Max Act: 5.9303. Min Act: -0.1700
Data Index: 853125 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1803. Min Range: -6.1803
Max Act: 5.9303. Min Act: -0.1700
Data Index: 2522572 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1803. Min Range: -6.1803
Max Act: 5.8991. Min Act: -0.1700
Data Index: 163372 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1803. Min Range: -6.1803
Max Act: 5.8678. Min Act: -0.1700
Data Index: 7568275 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1803. Min Range: -6.1803
Max Act: 5.8678. Min Act: -0.1700
Data Index: 374719 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1803. Min Range: -6.1803
Max Act: 5.8053. Min Act: -0.1700
Data Index: 2694702 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1803. Min Range: -6.1803
Max Act: 5.8366. Min Act: -0.1700
Data Index: 744254 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1803. Min Range: -6.1803
Max Act: 5.8366. Min Act: -0.1700
Data Index: 6850931 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1803. Min Range: -6.1803
Max Act: 5.8366. Min Act: -0.1700
Data Index: 7927056 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1803. Min Range: -6.1803
Max Act: 5.8366. Min Act: -0.1700
Data Index: 2522574 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1803. Min Range: -6.1803
Max Act: 5.8053. Min Act: -0.1700
Data Index: 7782505 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1803. Min Range: -6.1803
Max Act: 5.7741. Min Act: -0.1700
Data Index: 104668 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1803. Min Range: -6.1803
Max Act: 5.7428. Min Act: -0.1700
Data Index: 8083550 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1803. Min Range: -6.1803
Max Act: 5.7741. Min Act: -0.1700
Data Index: 8149332 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1803. Min Range: -6.1803
Max Act: 5.8053. Min Act: -0.1700
Data Index: 98051 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1803. Min Range: -6.1803
Max Act: 5.7428. Min Act: -0.1700
Data Index: 5679210 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1803. Min Range: -6.1803
Max Act: 5.6491. Min Act: -0.1700
Data Index: 4599576 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1803. Min Range: -6.1803
Max Act: 5.7428. Min Act: -0.1700
Data Index: 5984971 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #19