Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3648 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8170. Min Range: -5.8170
Max Act: 5.8170. Min Act: -0.1700
Data Index: 6952414 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8170. Min Range: -5.8170
Max Act: 5.7857. Min Act: -0.1700
Data Index: 5088159 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8170. Min Range: -5.8170
Max Act: 5.7545. Min Act: -0.1700
Data Index: 7041648 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8170. Min Range: -5.8170
Max Act: 5.7857. Min Act: -0.1700
Data Index: 4541632 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8170. Min Range: -5.8170
Max Act: 5.7232. Min Act: -0.1700
Data Index: 7066824 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8170. Min Range: -5.8170
Max Act: 5.6920. Min Act: -0.1700
Data Index: 1683756 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8170. Min Range: -5.8170
Max Act: 5.6607. Min Act: -0.1700
Data Index: 8223199 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8170. Min Range: -5.8170
Max Act: 5.6607. Min Act: -0.1700
Data Index: 3227216 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8170. Min Range: -5.8170
Max Act: 5.5670. Min Act: -0.1700
Data Index: 302338 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8170. Min Range: -5.8170
Max Act: 5.5670. Min Act: -0.1700
Data Index: 7340887 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8170. Min Range: -5.8170
Max Act: 5.5670. Min Act: -0.1700
Data Index: 8598802 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8170. Min Range: -5.8170
Max Act: 5.5045. Min Act: -0.1700
Data Index: 4706229 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8170. Min Range: -5.8170
Max Act: 5.5045. Min Act: -0.1700
Data Index: 2152146 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8170. Min Range: -5.8170
Max Act: 5.4732. Min Act: -0.1700
Data Index: 2003885 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8170. Min Range: -5.8170
Max Act: 5.4732. Min Act: -0.1700
Data Index: 3643418 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8170. Min Range: -5.8170
Max Act: 5.5045. Min Act: -0.1700
Data Index: 7102242 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8170. Min Range: -5.8170
Max Act: 5.4732. Min Act: -0.1700
Data Index: 6490887 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8170. Min Range: -5.8170
Max Act: 5.4732. Min Act: -0.1700
Data Index: 5130627 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8170. Min Range: -5.8170
Max Act: 5.4107. Min Act: -0.1700
Data Index: 1735109 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8170. Min Range: -5.8170
Max Act: 5.4107. Min Act: -0.1700
Data Index: 3053477 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19