Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3517 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3042. Min Range: -6.3042
Max Act: 6.3042. Min Act: -0.1700
Data Index: 7215820 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3042. Min Range: -6.3042
Max Act: 6.3042. Min Act: -0.1700
Data Index: 6601496 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3042. Min Range: -6.3042
Max Act: 6.1167. Min Act: -0.1700
Data Index: 4778156 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3042. Min Range: -6.3042
Max Act: 5.9605. Min Act: -0.1700
Data Index: 1960127 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3042. Min Range: -6.3042
Max Act: 5.9605. Min Act: -0.1700
Data Index: 2688994 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3042. Min Range: -6.3042
Max Act: 5.9605. Min Act: -0.1700
Data Index: 1934281 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3042. Min Range: -6.3042
Max Act: 5.9292. Min Act: -0.1700
Data Index: 3293480 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3042. Min Range: -6.3042
Max Act: 5.8980. Min Act: -0.1700
Data Index: 8159753 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3042. Min Range: -6.3042
Max Act: 5.8667. Min Act: -0.1700
Data Index: 5123811 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3042. Min Range: -6.3042
Max Act: 5.8667. Min Act: -0.1700
Data Index: 1501442 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3042. Min Range: -6.3042
Max Act: 5.8667. Min Act: -0.1700
Data Index: 4355873 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3042. Min Range: -6.3042
Max Act: 5.8355. Min Act: -0.1700
Data Index: 2539380 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3042. Min Range: -6.3042
Max Act: 5.8355. Min Act: -0.1700
Data Index: 4993762 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3042. Min Range: -6.3042
Max Act: 5.8042. Min Act: -0.1700
Data Index: 5132304 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3042. Min Range: -6.3042
Max Act: 5.8042. Min Act: -0.1700
Data Index: 8559227 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3042. Min Range: -6.3042
Max Act: 5.8042. Min Act: -0.1700
Data Index: 2623036 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3042. Min Range: -6.3042
Max Act: 5.7730. Min Act: -0.1700
Data Index: 7106227 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3042. Min Range: -6.3042
Max Act: 5.7730. Min Act: -0.1700
Data Index: 4456586 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3042. Min Range: -6.3042
Max Act: 5.7730. Min Act: -0.1700
Data Index: 8516569 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3042. Min Range: -6.3042
Max Act: 5.7417. Min Act: -0.1700
Data Index: 97574 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19