Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2884 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1969. Min Range: -6.1969
Max Act: 6.1969. Min Act: -0.1700
Data Index: 4828472 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1969. Min Range: -6.1969
Max Act: 6.1344. Min Act: -0.1700
Data Index: 1756374 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1969. Min Range: -6.1969
Max Act: 6.1344. Min Act: -0.1700
Data Index: 582599 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1969. Min Range: -6.1969
Max Act: 6.0719. Min Act: -0.1700
Data Index: 3388779 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1969. Min Range: -6.1969
Max Act: 6.0406. Min Act: -0.1700
Data Index: 6425012 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1969. Min Range: -6.1969
Max Act: 6.0406. Min Act: -0.1700
Data Index: 3347769 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1969. Min Range: -6.1969
Max Act: 6.0094. Min Act: -0.1700
Data Index: 4283682 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1969. Min Range: -6.1969
Max Act: 5.9781. Min Act: -0.1700
Data Index: 13400 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1969. Min Range: -6.1969
Max Act: 5.9781. Min Act: -0.1700
Data Index: 3646881 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1969. Min Range: -6.1969
Max Act: 5.9781. Min Act: -0.1700
Data Index: 1273841 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1969. Min Range: -6.1969
Max Act: 5.9781. Min Act: -0.1700
Data Index: 4709093 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1969. Min Range: -6.1969
Max Act: 5.9469. Min Act: -0.1700
Data Index: 4759495 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1969. Min Range: -6.1969
Max Act: 5.9469. Min Act: -0.1700
Data Index: 3455519 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1969. Min Range: -6.1969
Max Act: 5.9156. Min Act: -0.1700
Data Index: 4821895 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1969. Min Range: -6.1969
Max Act: 5.9156. Min Act: -0.1700
Data Index: 6250899 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1969. Min Range: -6.1969
Max Act: 5.9156. Min Act: -0.1700
Data Index: 6203763 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1969. Min Range: -6.1969
Max Act: 5.9469. Min Act: -0.1700
Data Index: 5968063 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1969. Min Range: -6.1969
Max Act: 5.8844. Min Act: -0.1700
Data Index: 4069471 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1969. Min Range: -6.1969
Max Act: 5.8844. Min Act: -0.1700
Data Index: 2286354 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1969. Min Range: -6.1969
Max Act: 5.8844. Min Act: -0.1700
Data Index: 1975063 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #19