Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2462 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2388. Min Range: -7.2388
Max Act: 7.2388. Min Act: -0.1700
Data Index: 5873390 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2388. Min Range: -7.2388
Max Act: 7.0513. Min Act: -0.1700
Data Index: 5239697 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2388. Min Range: -7.2388
Max Act: 6.9888. Min Act: -0.1700
Data Index: 7346079 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2388. Min Range: -7.2388
Max Act: 6.8326. Min Act: -0.1700
Data Index: 4225261 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2388. Min Range: -7.2388
Max Act: 6.7701. Min Act: -0.1700
Data Index: 2555145 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2388. Min Range: -7.2388
Max Act: 6.7388. Min Act: -0.1700
Data Index: 6488689 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2388. Min Range: -7.2388
Max Act: 6.7076. Min Act: -0.1700
Data Index: 5610003 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2388. Min Range: -7.2388
Max Act: 6.7076. Min Act: -0.1700
Data Index: 291284 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2388. Min Range: -7.2388
Max Act: 6.6763. Min Act: -0.1700
Data Index: 2838316 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2388. Min Range: -7.2388
Max Act: 6.6451. Min Act: -0.1700
Data Index: 3216721 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2388. Min Range: -7.2388
Max Act: 6.6138. Min Act: -0.1700
Data Index: 3939236 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2388. Min Range: -7.2388
Max Act: 6.6451. Min Act: -0.1700
Data Index: 4798502 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2388. Min Range: -7.2388
Max Act: 6.5826. Min Act: -0.1700
Data Index: 8713687 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2388. Min Range: -7.2388
Max Act: 6.5826. Min Act: -0.1700
Data Index: 2793199 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2388. Min Range: -7.2388
Max Act: 6.5513. Min Act: -0.1700
Data Index: 854020 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2388. Min Range: -7.2388
Max Act: 6.5513. Min Act: -0.1700
Data Index: 6420498 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2388. Min Range: -7.2388
Max Act: 6.5513. Min Act: -0.1700
Data Index: 8330530 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2388. Min Range: -7.2388
Max Act: 6.5201. Min Act: -0.1700
Data Index: 2415019 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2388. Min Range: -7.2388
Max Act: 6.5201. Min Act: -0.1700
Data Index: 7822535 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2388. Min Range: -7.2388
Max Act: 6.4576. Min Act: -0.1700
Data Index: 5205112 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19