Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4990 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4132. Min Range: -5.4132
Max Act: 5.3819. Min Act: -0.1700
Data Index: 5002096 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4132. Min Range: -5.4132
Max Act: 5.4132. Min Act: -0.1700
Data Index: 5533262 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4132. Min Range: -5.4132
Max Act: 5.3819. Min Act: -0.1700
Data Index: 6133309 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4132. Min Range: -5.4132
Max Act: 5.3819. Min Act: -0.1700
Data Index: 8597663 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4132. Min Range: -5.4132
Max Act: 5.3819. Min Act: -0.1700
Data Index: 6118670 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4132. Min Range: -5.4132
Max Act: 5.3507. Min Act: -0.1700
Data Index: 5486523 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4132. Min Range: -5.4132
Max Act: 5.3194. Min Act: -0.1700
Data Index: 3965968 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4132. Min Range: -5.4132
Max Act: 5.3194. Min Act: -0.1700
Data Index: 8740214 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4132. Min Range: -5.4132
Max Act: 5.3194. Min Act: -0.1700
Data Index: 8661798 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4132. Min Range: -5.4132
Max Act: 5.2882. Min Act: -0.1700
Data Index: 1112112 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4132. Min Range: -5.4132
Max Act: 5.3194. Min Act: -0.1700
Data Index: 2541084 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4132. Min Range: -5.4132
Max Act: 5.2569. Min Act: -0.1700
Data Index: 4955080 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4132. Min Range: -5.4132
Max Act: 5.2257. Min Act: -0.1700
Data Index: 6899711 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4132. Min Range: -5.4132
Max Act: 5.2569. Min Act: -0.1700
Data Index: 1199851 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4132. Min Range: -5.4132
Max Act: 5.1944. Min Act: -0.1700
Data Index: 540375 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4132. Min Range: -5.4132
Max Act: 5.1944. Min Act: -0.1700
Data Index: 2745537 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4132. Min Range: -5.4132
Max Act: 5.1944. Min Act: -0.1699
Data Index: 4793027 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4132. Min Range: -5.4132
Max Act: 5.2257. Min Act: -0.1700
Data Index: 4995504 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4132. Min Range: -5.4132
Max Act: 5.2257. Min Act: -0.1700
Data Index: 2638107 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4132. Min Range: -5.4132
Max Act: 5.1632. Min Act: -0.1700
Data Index: 4950900 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19