Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4459 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2096. Min Range: -9.2096
Max Act: 9.2096. Min Act: -0.1700
Data Index: 415561 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2096. Min Range: -9.2096
Max Act: 8.7096. Min Act: -0.1700
Data Index: 3952477 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2096. Min Range: -9.2096
Max Act: 8.7096. Min Act: -0.1700
Data Index: 4835240 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2096. Min Range: -9.2096
Max Act: 8.5846. Min Act: -0.1700
Data Index: 2979520 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2096. Min Range: -9.2096
Max Act: 8.5846. Min Act: -0.1700
Data Index: 4385279 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2096. Min Range: -9.2096
Max Act: 8.5846. Min Act: -0.1700
Data Index: 6622680 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2096. Min Range: -9.2096
Max Act: 8.5846. Min Act: -0.1700
Data Index: 1144735 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2096. Min Range: -9.2096
Max Act: 8.5846. Min Act: -0.1700
Data Index: 6866075 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2096. Min Range: -9.2096
Max Act: 8.5846. Min Act: -0.1700
Data Index: 3785605 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2096. Min Range: -9.2096
Max Act: 8.5221. Min Act: -0.1700
Data Index: 1651131 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2096. Min Range: -9.2096
Max Act: 8.5221. Min Act: -0.1700
Data Index: 6025209 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2096. Min Range: -9.2096
Max Act: 8.5221. Min Act: -0.1700
Data Index: 2244402 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2096. Min Range: -9.2096
Max Act: 8.5221. Min Act: -0.1700
Data Index: 5707197 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2096. Min Range: -9.2096
Max Act: 8.5221. Min Act: -0.1700
Data Index: 6526485 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2096. Min Range: -9.2096
Max Act: 8.4596. Min Act: -0.1700
Data Index: 1453496 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2096. Min Range: -9.2096
Max Act: 8.4596. Min Act: -0.1700
Data Index: 3825964 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2096. Min Range: -9.2096
Max Act: 8.4596. Min Act: -0.1700
Data Index: 6709567 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2096. Min Range: -9.2096
Max Act: 8.4596. Min Act: -0.1700
Data Index: 329814 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2096. Min Range: -9.2096
Max Act: 8.4596. Min Act: -0.1700
Data Index: 1322030 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2096. Min Range: -9.2096
Max Act: 8.4596. Min Act: -0.1700
Data Index: 6145502 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19