Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5458 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4889. Min Range: -7.4889
Max Act: 7.4889. Min Act: -0.1700
Data Index: 5650140 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4889. Min Range: -7.4889
Max Act: 7.3639. Min Act: -0.1700
Data Index: 2721917 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4889. Min Range: -7.4889
Max Act: 7.3639. Min Act: -0.1700
Data Index: 3572561 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4889. Min Range: -7.4889
Max Act: 7.2702. Min Act: -0.1700
Data Index: 6193848 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4889. Min Range: -7.4889
Max Act: 7.2077. Min Act: -0.1700
Data Index: 5823308 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4889. Min Range: -7.4889
Max Act: 7.1764. Min Act: -0.1700
Data Index: 8500346 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4889. Min Range: -7.4889
Max Act: 7.1452. Min Act: -0.1700
Data Index: 6985608 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4889. Min Range: -7.4889
Max Act: 7.1452. Min Act: -0.1700
Data Index: 4115990 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4889. Min Range: -7.4889
Max Act: 7.1139. Min Act: -0.1700
Data Index: 7106848 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4889. Min Range: -7.4889
Max Act: 7.1139. Min Act: -0.1700
Data Index: 1747488 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4889. Min Range: -7.4889
Max Act: 7.0202. Min Act: -0.1700
Data Index: 2234817 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4889. Min Range: -7.4889
Max Act: 7.0827. Min Act: -0.1700
Data Index: 6181423 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4889. Min Range: -7.4889
Max Act: 7.0202. Min Act: -0.1700
Data Index: 6321546 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4889. Min Range: -7.4889
Max Act: 7.0202. Min Act: -0.1700
Data Index: 3724350 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4889. Min Range: -7.4889
Max Act: 6.9889. Min Act: -0.1700
Data Index: 2128334 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4889. Min Range: -7.4889
Max Act: 6.9889. Min Act: -0.1700
Data Index: 1209392 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4889. Min Range: -7.4889
Max Act: 6.8639. Min Act: -0.1700
Data Index: 6967095 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4889. Min Range: -7.4889
Max Act: 6.8952. Min Act: -0.1700
Data Index: 6340214 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4889. Min Range: -7.4889
Max Act: 6.8952. Min Act: -0.1700
Data Index: 7517222 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4889. Min Range: -7.4889
Max Act: 6.9264. Min Act: -0.1700
Data Index: 4856294 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19