Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 908 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8527. Min Range: -5.8527
Max Act: 5.8527. Min Act: -0.1700
Data Index: 2989209 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8527. Min Range: -5.8527
Max Act: 5.7277. Min Act: -0.1700
Data Index: 7178549 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8527. Min Range: -5.8527
Max Act: 5.6965. Min Act: -0.1700
Data Index: 6331714 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8527. Min Range: -5.8527
Max Act: 5.5402. Min Act: -0.1700
Data Index: 1491943 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8527. Min Range: -5.8527
Max Act: 5.5090. Min Act: -0.1700
Data Index: 8121742 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8527. Min Range: -5.8527
Max Act: 5.4465. Min Act: -0.1700
Data Index: 4923987 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8527. Min Range: -5.8527
Max Act: 5.3840. Min Act: -0.1700
Data Index: 5038211 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8527. Min Range: -5.8527
Max Act: 5.3840. Min Act: -0.1700
Data Index: 8517097 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8527. Min Range: -5.8527
Max Act: 5.3527. Min Act: -0.1700
Data Index: 723846 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8527. Min Range: -5.8527
Max Act: 5.2902. Min Act: -0.1700
Data Index: 400385 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8527. Min Range: -5.8527
Max Act: 5.2590. Min Act: -0.1700
Data Index: 1826945 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8527. Min Range: -5.8527
Max Act: 5.2590. Min Act: -0.1700
Data Index: 1281912 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8527. Min Range: -5.8527
Max Act: 5.2590. Min Act: -0.1700
Data Index: 2573259 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8527. Min Range: -5.8527
Max Act: 5.2590. Min Act: -0.1700
Data Index: 431180 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8527. Min Range: -5.8527
Max Act: 5.2277. Min Act: -0.1700
Data Index: 1116459 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8527. Min Range: -5.8527
Max Act: 5.1965. Min Act: -0.1700
Data Index: 4006564 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8527. Min Range: -5.8527
Max Act: 5.1965. Min Act: -0.1700
Data Index: 7463628 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8527. Min Range: -5.8527
Max Act: 5.1965. Min Act: -0.1700
Data Index: 1781765 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8527. Min Range: -5.8527
Max Act: 5.1652. Min Act: -0.1700
Data Index: 6290225 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8527. Min Range: -5.8527
Max Act: 5.1340. Min Act: -0.1700
Data Index: 1299635 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19