Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2426 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6075. Min Range: -10.6075
Max Act: 10.6075. Min Act: -0.1700
Data Index: 2233662 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6075. Min Range: -10.6075
Max Act: 10.1700. Min Act: -0.1700
Data Index: 2642453 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6075. Min Range: -10.6075
Max Act: 10.0450. Min Act: -0.1700
Data Index: 7818224 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6075. Min Range: -10.6075
Max Act: 9.9825. Min Act: -0.1700
Data Index: 4782843 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6075. Min Range: -10.6075
Max Act: 9.9825. Min Act: -0.1700
Data Index: 7761972 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6075. Min Range: -10.6075
Max Act: 9.9825. Min Act: -0.1700
Data Index: 6061860 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6075. Min Range: -10.6075
Max Act: 9.8575. Min Act: -0.1700
Data Index: 409800 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6075. Min Range: -10.6075
Max Act: 9.8575. Min Act: -0.1700
Data Index: 4179946 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6075. Min Range: -10.6075
Max Act: 9.8575. Min Act: -0.1700
Data Index: 7818239 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6075. Min Range: -10.6075
Max Act: 9.8575. Min Act: -0.1700
Data Index: 6408435 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6075. Min Range: -10.6075
Max Act: 9.8575. Min Act: -0.1700
Data Index: 7761970 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6075. Min Range: -10.6075
Max Act: 9.7950. Min Act: -0.1700
Data Index: 8610757 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6075. Min Range: -10.6075
Max Act: 9.7950. Min Act: -0.1700
Data Index: 8778901 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6075. Min Range: -10.6075
Max Act: 9.7325. Min Act: -0.1700
Data Index: 3259449 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6075. Min Range: -10.6075
Max Act: 9.7325. Min Act: -0.1700
Data Index: 1688576 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6075. Min Range: -10.6075
Max Act: 9.7325. Min Act: -0.1700
Data Index: 3928332 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6075. Min Range: -10.6075
Max Act: 9.6700. Min Act: -0.1700
Data Index: 1778164 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6075. Min Range: -10.6075
Max Act: 9.7325. Min Act: -0.1700
Data Index: 1244684 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6075. Min Range: -10.6075
Max Act: 9.6700. Min Act: -0.1700
Data Index: 7818238 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6075. Min Range: -10.6075
Max Act: 9.6700. Min Act: -0.1700
Data Index: 4223872 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19