Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3511 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8912. Min Range: -3.8912
Max Act: 3.8912. Min Act: -0.1700
Data Index: 3121095 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8912. Min Range: -3.8912
Max Act: 3.7974. Min Act: -0.1700
Data Index: 3096459 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8912. Min Range: -3.8912
Max Act: 3.7974. Min Act: -0.1700
Data Index: 5612795 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8912. Min Range: -3.8912
Max Act: 3.8287. Min Act: -0.1700
Data Index: 8453327 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8912. Min Range: -3.8912
Max Act: 3.7348. Min Act: -0.1700
Data Index: 5345501 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8912. Min Range: -3.8912
Max Act: 3.7661. Min Act: -0.1700
Data Index: 8611910 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8912. Min Range: -3.8912
Max Act: 3.7348. Min Act: -0.1700
Data Index: 6751802 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8912. Min Range: -3.8912
Max Act: 3.7348. Min Act: -0.1700
Data Index: 5625690 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8912. Min Range: -3.8912
Max Act: 3.7348. Min Act: -0.1700
Data Index: 3560489 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8912. Min Range: -3.8912
Max Act: 3.7036. Min Act: -0.1700
Data Index: 574587 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8912. Min Range: -3.8912
Max Act: 3.6410. Min Act: -0.1700
Data Index: 6946768 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8912. Min Range: -3.8912
Max Act: 3.6410. Min Act: -0.1700
Data Index: 7478637 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8912. Min Range: -3.8912
Max Act: 3.6410. Min Act: -0.1700
Data Index: 5963841 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8912. Min Range: -3.8912
Max Act: 3.6410. Min Act: -0.1700
Data Index: 7353880 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8912. Min Range: -3.8912
Max Act: 3.6410. Min Act: -0.1700
Data Index: 1853809 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8912. Min Range: -3.8912
Max Act: 3.6097. Min Act: -0.1700
Data Index: 7478625 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8912. Min Range: -3.8912
Max Act: 3.5784. Min Act: -0.1700
Data Index: 5839198 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8912. Min Range: -3.8912
Max Act: 3.6410. Min Act: -0.1700
Data Index: 602270 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8912. Min Range: -3.8912
Max Act: 3.6097. Min Act: -0.1700
Data Index: 411629 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8912. Min Range: -3.8912
Max Act: 3.6097. Min Act: -0.1700
Data Index: 8713680 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19