Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2960 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0180. Min Range: -5.0180
Max Act: 5.0180. Min Act: -0.1700
Data Index: 7579234 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0180. Min Range: -5.0180
Max Act: 4.9868. Min Act: -0.1700
Data Index: 509228 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0180. Min Range: -5.0180
Max Act: 4.8618. Min Act: -0.1700
Data Index: 7993540 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0180. Min Range: -5.0180
Max Act: 4.8618. Min Act: -0.1700
Data Index: 8407908 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0180. Min Range: -5.0180
Max Act: 4.8618. Min Act: -0.1700
Data Index: 2476207 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0180. Min Range: -5.0180
Max Act: 4.8618. Min Act: -0.1700
Data Index: 2511758 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0180. Min Range: -5.0180
Max Act: 4.8618. Min Act: -0.1700
Data Index: 4481424 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0180. Min Range: -5.0180
Max Act: 4.7993. Min Act: -0.1700
Data Index: 3414102 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0180. Min Range: -5.0180
Max Act: 4.7993. Min Act: -0.1700
Data Index: 7585543 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0180. Min Range: -5.0180
Max Act: 4.7993. Min Act: -0.1700
Data Index: 4379584 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0180. Min Range: -5.0180
Max Act: 4.7680. Min Act: -0.1700
Data Index: 6647646 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0180. Min Range: -5.0180
Max Act: 4.7055. Min Act: -0.1700
Data Index: 792142 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0180. Min Range: -5.0180
Max Act: 4.6743. Min Act: -0.1700
Data Index: 2509417 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0180. Min Range: -5.0180
Max Act: 4.6743. Min Act: -0.1700
Data Index: 1686373 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0180. Min Range: -5.0180
Max Act: 4.6117. Min Act: -0.1700
Data Index: 1709406 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0180. Min Range: -5.0180
Max Act: 4.6117. Min Act: -0.1700
Data Index: 3351725 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0180. Min Range: -5.0180
Max Act: 4.6430. Min Act: -0.1700
Data Index: 2712940 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0180. Min Range: -5.0180
Max Act: 4.6117. Min Act: -0.1700
Data Index: 3415706 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0180. Min Range: -5.0180
Max Act: 4.5805. Min Act: -0.1700
Data Index: 1332829 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0180. Min Range: -5.0180
Max Act: 4.6117. Min Act: -0.1700
Data Index: 5759126 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19