Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4565 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1371. Min Range: -7.1371
Max Act: 7.1371. Min Act: -0.1700
Data Index: 8084895 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1371. Min Range: -7.1371
Max Act: 6.9184. Min Act: -0.1700
Data Index: 8589537 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1371. Min Range: -7.1371
Max Act: 6.8871. Min Act: -0.1700
Data Index: 1686452 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1371. Min Range: -7.1371
Max Act: 6.8246. Min Act: -0.1700
Data Index: 767351 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1371. Min Range: -7.1371
Max Act: 6.6996. Min Act: -0.1700
Data Index: 4946871 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1371. Min Range: -7.1371
Max Act: 6.6684. Min Act: -0.1700
Data Index: 3648929 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1371. Min Range: -7.1371
Max Act: 6.6684. Min Act: -0.1700
Data Index: 8743683 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1371. Min Range: -7.1371
Max Act: 6.6059. Min Act: -0.1700
Data Index: 1613042 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1371. Min Range: -7.1371
Max Act: 6.5746. Min Act: -0.1700
Data Index: 5027278 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1371. Min Range: -7.1371
Max Act: 6.5434. Min Act: -0.1700
Data Index: 4580332 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1371. Min Range: -7.1371
Max Act: 6.5121. Min Act: -0.1700
Data Index: 5375217 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1371. Min Range: -7.1371
Max Act: 6.5121. Min Act: -0.1700
Data Index: 5218161 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1371. Min Range: -7.1371
Max Act: 6.4809. Min Act: -0.1700
Data Index: 6593936 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1371. Min Range: -7.1371
Max Act: 6.5121. Min Act: -0.1700
Data Index: 6430584 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1371. Min Range: -7.1371
Max Act: 6.4184. Min Act: -0.1700
Data Index: 7922968 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1371. Min Range: -7.1371
Max Act: 6.4184. Min Act: -0.1700
Data Index: 4769423 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1371. Min Range: -7.1371
Max Act: 6.3871. Min Act: -0.1700
Data Index: 2544160 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1371. Min Range: -7.1371
Max Act: 6.4184. Min Act: -0.1700
Data Index: 1167666 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1371. Min Range: -7.1371
Max Act: 6.4184. Min Act: -0.1700
Data Index: 7327787 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1371. Min Range: -7.1371
Max Act: 6.4184. Min Act: -0.1700
Data Index: 1245378 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19