Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3510 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6587. Min Range: -7.6587
Max Act: 7.6587. Min Act: -0.1700
Data Index: 3187663 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6587. Min Range: -7.6587
Max Act: 7.4712. Min Act: -0.1700
Data Index: 1664289 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6587. Min Range: -7.6587
Max Act: 7.2837. Min Act: -0.1700
Data Index: 2453020 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6587. Min Range: -7.6587
Max Act: 7.2525. Min Act: -0.1700
Data Index: 5526993 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6587. Min Range: -7.6587
Max Act: 7.2525. Min Act: -0.1700
Data Index: 1126262 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6587. Min Range: -7.6587
Max Act: 7.1275. Min Act: -0.1700
Data Index: 8758760 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6587. Min Range: -7.6587
Max Act: 7.0962. Min Act: -0.1700
Data Index: 1778814 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6587. Min Range: -7.6587
Max Act: 7.0650. Min Act: -0.1700
Data Index: 4442371 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6587. Min Range: -7.6587
Max Act: 6.9400. Min Act: -0.1700
Data Index: 6637819 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6587. Min Range: -7.6587
Max Act: 6.9400. Min Act: -0.1700
Data Index: 1898935 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6587. Min Range: -7.6587
Max Act: 6.9087. Min Act: -0.1700
Data Index: 1044725 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6587. Min Range: -7.6587
Max Act: 6.9087. Min Act: -0.1700
Data Index: 8717899 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6587. Min Range: -7.6587
Max Act: 6.8462. Min Act: -0.1700
Data Index: 8052210 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6587. Min Range: -7.6587
Max Act: 6.8462. Min Act: -0.1700
Data Index: 4491048 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6587. Min Range: -7.6587
Max Act: 6.8150. Min Act: -0.1700
Data Index: 4329595 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6587. Min Range: -7.6587
Max Act: 6.8150. Min Act: -0.1700
Data Index: 2923763 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6587. Min Range: -7.6587
Max Act: 6.8150. Min Act: -0.1700
Data Index: 6254347 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6587. Min Range: -7.6587
Max Act: 6.7837. Min Act: -0.1700
Data Index: 3694408 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6587. Min Range: -7.6587
Max Act: 6.7837. Min Act: -0.1700
Data Index: 2705579 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6587. Min Range: -7.6587
Max Act: 6.7525. Min Act: -0.1700
Data Index: 5760154 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19