Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2126 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0260. Min Range: -7.0260
Max Act: 7.0260. Min Act: -0.1700
Data Index: 3102253 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0260. Min Range: -7.0260
Max Act: 6.9010. Min Act: -0.1700
Data Index: 404963 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0260. Min Range: -7.0260
Max Act: 6.8697. Min Act: -0.1700
Data Index: 6561468 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0260. Min Range: -7.0260
Max Act: 6.8385. Min Act: -0.1700
Data Index: 5142339 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0260. Min Range: -7.0260
Max Act: 6.8072. Min Act: -0.1700
Data Index: 5241429 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0260. Min Range: -7.0260
Max Act: 6.8072. Min Act: -0.1700
Data Index: 3935979 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0260. Min Range: -7.0260
Max Act: 6.7135. Min Act: -0.1700
Data Index: 7363854 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0260. Min Range: -7.0260
Max Act: 6.7135. Min Act: -0.1700
Data Index: 5536811 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0260. Min Range: -7.0260
Max Act: 6.7135. Min Act: -0.1700
Data Index: 5323775 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0260. Min Range: -7.0260
Max Act: 6.7135. Min Act: -0.1700
Data Index: 1339869 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0260. Min Range: -7.0260
Max Act: 6.7135. Min Act: -0.1700
Data Index: 1573215 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0260. Min Range: -7.0260
Max Act: 6.7135. Min Act: -0.1700
Data Index: 1996294 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0260. Min Range: -7.0260
Max Act: 6.6822. Min Act: -0.1700
Data Index: 6384158 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0260. Min Range: -7.0260
Max Act: 6.6822. Min Act: -0.1700
Data Index: 6489631 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0260. Min Range: -7.0260
Max Act: 6.6510. Min Act: -0.1700
Data Index: 1387855 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0260. Min Range: -7.0260
Max Act: 6.6822. Min Act: -0.1700
Data Index: 903895 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0260. Min Range: -7.0260
Max Act: 6.6822. Min Act: -0.1700
Data Index: 2638121 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0260. Min Range: -7.0260
Max Act: 6.6510. Min Act: -0.1700
Data Index: 2059695 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0260. Min Range: -7.0260
Max Act: 6.6510. Min Act: -0.1700
Data Index: 2021958 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0260. Min Range: -7.0260
Max Act: 6.6197. Min Act: -0.1700
Data Index: 1577410 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19