Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3699 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6869. Min Range: -9.6869
Max Act: 9.6869. Min Act: -0.1700
Data Index: 8088743 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6869. Min Range: -9.6869
Max Act: 9.6244. Min Act: -0.1700
Data Index: 7637082 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6869. Min Range: -9.6869
Max Act: 9.4369. Min Act: -0.1700
Data Index: 768093 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6869. Min Range: -9.6869
Max Act: 9.4369. Min Act: -0.1700
Data Index: 3039366 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6869. Min Range: -9.6869
Max Act: 9.4369. Min Act: -0.1700
Data Index: 6120975 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6869. Min Range: -9.6869
Max Act: 9.3744. Min Act: -0.1700
Data Index: 3530578 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6869. Min Range: -9.6869
Max Act: 9.3744. Min Act: -0.1700
Data Index: 123454 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6869. Min Range: -9.6869
Max Act: 9.3744. Min Act: -0.1700
Data Index: 8728454 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6869. Min Range: -9.6869
Max Act: 9.3744. Min Act: -0.1700
Data Index: 1996656 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6869. Min Range: -9.6869
Max Act: 9.1869. Min Act: -0.1700
Data Index: 3642969 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6869. Min Range: -9.6869
Max Act: 9.1869. Min Act: -0.1700
Data Index: 909798 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6869. Min Range: -9.6869
Max Act: 9.1244. Min Act: -0.1700
Data Index: 4142981 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6869. Min Range: -9.6869
Max Act: 9.1244. Min Act: -0.1700
Data Index: 7232566 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6869. Min Range: -9.6869
Max Act: 9.1244. Min Act: -0.1700
Data Index: 8331548 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6869. Min Range: -9.6869
Max Act: 9.0619. Min Act: -0.1700
Data Index: 5733429 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6869. Min Range: -9.6869
Max Act: 9.0619. Min Act: -0.1700
Data Index: 8644848 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6869. Min Range: -9.6869
Max Act: 9.0619. Min Act: -0.1700
Data Index: 1656787 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6869. Min Range: -9.6869
Max Act: 9.0619. Min Act: -0.1700
Data Index: 6517807 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6869. Min Range: -9.6869
Max Act: 9.0619. Min Act: -0.1700
Data Index: 2298608 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6869. Min Range: -9.6869
Max Act: 8.9994. Min Act: -0.1700
Data Index: 237240 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19