Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2602 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4465. Min Range: -7.4465
Max Act: 7.4465. Min Act: -0.1700
Data Index: 5680382 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4465. Min Range: -7.4465
Max Act: 7.3840. Min Act: -0.1699
Data Index: 5725367 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4465. Min Range: -7.4465
Max Act: 7.3215. Min Act: -0.1700
Data Index: 1739541 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4465. Min Range: -7.4465
Max Act: 7.2278. Min Act: -0.1700
Data Index: 6154423 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4465. Min Range: -7.4465
Max Act: 7.1965. Min Act: -0.1700
Data Index: 4385515 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4465. Min Range: -7.4465
Max Act: 7.1340. Min Act: -0.1700
Data Index: 7736999 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4465. Min Range: -7.4465
Max Act: 7.1028. Min Act: -0.1700
Data Index: 2982806 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4465. Min Range: -7.4465
Max Act: 7.0715. Min Act: -0.1700
Data Index: 1978429 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4465. Min Range: -7.4465
Max Act: 6.9778. Min Act: -0.1700
Data Index: 4718329 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4465. Min Range: -7.4465
Max Act: 7.0090. Min Act: -0.1700
Data Index: 569691 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4465. Min Range: -7.4465
Max Act: 6.9153. Min Act: -0.1700
Data Index: 196021 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4465. Min Range: -7.4465
Max Act: 6.9465. Min Act: -0.1700
Data Index: 1588884 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4465. Min Range: -7.4465
Max Act: 6.9465. Min Act: -0.1700
Data Index: 5229029 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4465. Min Range: -7.4465
Max Act: 6.9153. Min Act: -0.1700
Data Index: 702791 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4465. Min Range: -7.4465
Max Act: 6.9153. Min Act: -0.1700
Data Index: 2073442 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4465. Min Range: -7.4465
Max Act: 6.8840. Min Act: -0.1700
Data Index: 4385530 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4465. Min Range: -7.4465
Max Act: 6.8840. Min Act: -0.1700
Data Index: 3362772 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4465. Min Range: -7.4465
Max Act: 6.8528. Min Act: -0.1700
Data Index: 3029474 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4465. Min Range: -7.4465
Max Act: 6.8528. Min Act: -0.1700
Data Index: 4385520 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4465. Min Range: -7.4465
Max Act: 6.8528. Min Act: -0.1700
Data Index: 4091142 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19