Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6002 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8659. Min Range: -6.8659
Max Act: 6.8659. Min Act: -0.1700
Data Index: 3717579 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8659. Min Range: -6.8659
Max Act: 6.7096. Min Act: -0.1700
Data Index: 8009908 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8659. Min Range: -6.8659
Max Act: 6.7096. Min Act: -0.1700
Data Index: 4957020 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8659. Min Range: -6.8659
Max Act: 6.5221. Min Act: -0.1700
Data Index: 1690960 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8659. Min Range: -6.8659
Max Act: 6.4284. Min Act: -0.1700
Data Index: 4666929 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8659. Min Range: -6.8659
Max Act: 6.3971. Min Act: -0.1700
Data Index: 4231807 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8659. Min Range: -6.8659
Max Act: 6.3971. Min Act: -0.1700
Data Index: 6577599 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8659. Min Range: -6.8659
Max Act: 6.3971. Min Act: -0.1700
Data Index: 8407443 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8659. Min Range: -6.8659
Max Act: 6.3659. Min Act: -0.1700
Data Index: 3610278 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8659. Min Range: -6.8659
Max Act: 6.3034. Min Act: -0.1700
Data Index: 7009380 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8659. Min Range: -6.8659
Max Act: 6.2721. Min Act: -0.1700
Data Index: 2169459 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8659. Min Range: -6.8659
Max Act: 6.2721. Min Act: -0.1700
Data Index: 4418000 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8659. Min Range: -6.8659
Max Act: 6.2409. Min Act: -0.1700
Data Index: 2715574 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8659. Min Range: -6.8659
Max Act: 6.2096. Min Act: -0.1700
Data Index: 6033773 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8659. Min Range: -6.8659
Max Act: 6.2096. Min Act: -0.1700
Data Index: 823812 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8659. Min Range: -6.8659
Max Act: 6.2096. Min Act: -0.1700
Data Index: 5798453 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8659. Min Range: -6.8659
Max Act: 6.1784. Min Act: -0.1700
Data Index: 2654291 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8659. Min Range: -6.8659
Max Act: 6.1784. Min Act: -0.1700
Data Index: 5898294 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8659. Min Range: -6.8659
Max Act: 6.1784. Min Act: -0.1700
Data Index: 2136888 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8659. Min Range: -6.8659
Max Act: 6.1471. Min Act: -0.1700
Data Index: 2100345 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19