Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 819 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6188. Min Range: -4.6188
Max Act: 4.6188. Min Act: -0.1700
Data Index: 4921866 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6188. Min Range: -4.6188
Max Act: 4.5563. Min Act: -0.1700
Data Index: 135024 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6188. Min Range: -4.6188
Max Act: 4.5250. Min Act: -0.1700
Data Index: 6265219 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6188. Min Range: -4.6188
Max Act: 4.5563. Min Act: -0.1700
Data Index: 8044922 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6188. Min Range: -4.6188
Max Act: 4.5250. Min Act: -0.1700
Data Index: 4670820 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6188. Min Range: -4.6188
Max Act: 4.5250. Min Act: -0.1700
Data Index: 3808739 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6188. Min Range: -4.6188
Max Act: 4.4938. Min Act: -0.1700
Data Index: 3253229 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6188. Min Range: -4.6188
Max Act: 4.4625. Min Act: -0.1700
Data Index: 4240290 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6188. Min Range: -4.6188
Max Act: 4.4625. Min Act: -0.1700
Data Index: 4874873 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6188. Min Range: -4.6188
Max Act: 4.4625. Min Act: -0.1700
Data Index: 3917012 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6188. Min Range: -4.6188
Max Act: 4.4625. Min Act: -0.1700
Data Index: 5639434 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6188. Min Range: -4.6188
Max Act: 4.4000. Min Act: -0.1700
Data Index: 8044921 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6188. Min Range: -4.6188
Max Act: 4.4000. Min Act: -0.1700
Data Index: 8044917 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6188. Min Range: -4.6188
Max Act: 4.4313. Min Act: -0.1700
Data Index: 8044916 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6188. Min Range: -4.6188
Max Act: 4.4000. Min Act: -0.1700
Data Index: 7255364 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6188. Min Range: -4.6188
Max Act: 4.3688. Min Act: -0.1700
Data Index: 7784920 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6188. Min Range: -4.6188
Max Act: 4.3688. Min Act: -0.1700
Data Index: 838955 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6188. Min Range: -4.6188
Max Act: 4.3688. Min Act: -0.1700
Data Index: 2372346 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6188. Min Range: -4.6188
Max Act: 4.3688. Min Act: -0.1700
Data Index: 1570300 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6188. Min Range: -4.6188
Max Act: 4.3688. Min Act: -0.1700
Data Index: 6548997 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19