Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3031 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9549. Min Range: -4.9549
Max Act: 4.9549. Min Act: -0.1700
Data Index: 3809514 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9549. Min Range: -4.9549
Max Act: 4.6111. Min Act: -0.1700
Data Index: 1646017 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9549. Min Range: -4.9549
Max Act: 4.5486. Min Act: -0.1700
Data Index: 1621474 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9549. Min Range: -4.9549
Max Act: 4.5799. Min Act: -0.1700
Data Index: 4131672 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9549. Min Range: -4.9549
Max Act: 4.5799. Min Act: -0.1700
Data Index: 6212782 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9549. Min Range: -4.9549
Max Act: 4.5174. Min Act: -0.1700
Data Index: 4334296 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9549. Min Range: -4.9549
Max Act: 4.4861. Min Act: -0.1700
Data Index: 491536 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9549. Min Range: -4.9549
Max Act: 4.4861. Min Act: -0.1700
Data Index: 8411158 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9549. Min Range: -4.9549
Max Act: 4.5174. Min Act: -0.1700
Data Index: 6819516 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9549. Min Range: -4.9549
Max Act: 4.4549. Min Act: -0.1700
Data Index: 1128250 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9549. Min Range: -4.9549
Max Act: 4.4861. Min Act: -0.1700
Data Index: 4266530 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9549. Min Range: -4.9549
Max Act: 4.4861. Min Act: -0.1700
Data Index: 24582 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9549. Min Range: -4.9549
Max Act: 4.4861. Min Act: -0.1700
Data Index: 4985205 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9549. Min Range: -4.9549
Max Act: 4.4549. Min Act: -0.1700
Data Index: 6342772 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9549. Min Range: -4.9549
Max Act: 4.4549. Min Act: -0.1700
Data Index: 2217735 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9549. Min Range: -4.9549
Max Act: 4.4549. Min Act: -0.1700
Data Index: 2032858 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9549. Min Range: -4.9549
Max Act: 4.4549. Min Act: -0.1700
Data Index: 4209862 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9549. Min Range: -4.9549
Max Act: 4.4549. Min Act: -0.1700
Data Index: 7132617 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9549. Min Range: -4.9549
Max Act: 4.4549. Min Act: -0.1700
Data Index: 4678114 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9549. Min Range: -4.9549
Max Act: 4.4861. Min Act: -0.1700
Data Index: 1687500 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19