Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 115 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6317. Min Range: -2.6317
Max Act: 2.6317. Min Act: -0.1700
Data Index: 483212 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6317. Min Range: -2.6317
Max Act: 2.6317. Min Act: -0.1700
Data Index: 2518870 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6317. Min Range: -2.6317
Max Act: 2.6156. Min Act: -0.1700
Data Index: 8032066 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6317. Min Range: -2.6317
Max Act: 2.5835. Min Act: -0.1700
Data Index: 4611912 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6317. Min Range: -2.6317
Max Act: 2.5835. Min Act: -0.1700
Data Index: 872548 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6317. Min Range: -2.6317
Max Act: 2.5512. Min Act: -0.1700
Data Index: 4641193 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6317. Min Range: -2.6317
Max Act: 2.5512. Min Act: -0.1700
Data Index: 2175190 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6317. Min Range: -2.6317
Max Act: 2.5189. Min Act: -0.1700
Data Index: 8052063 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6317. Min Range: -2.6317
Max Act: 2.5189. Min Act: -0.1700
Data Index: 168262 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6317. Min Range: -2.6317
Max Act: 2.5189. Min Act: -0.1700
Data Index: 3177978 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6317. Min Range: -2.6317
Max Act: 2.5027. Min Act: -0.1700
Data Index: 6201115 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6317. Min Range: -2.6317
Max Act: 2.5189. Min Act: -0.1700
Data Index: 76027 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6317. Min Range: -2.6317
Max Act: 2.5027. Min Act: -0.1700
Data Index: 8692080 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6317. Min Range: -2.6317
Max Act: 2.4865. Min Act: -0.1700
Data Index: 8649109 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6317. Min Range: -2.6317
Max Act: 2.4540. Min Act: -0.1700
Data Index: 5019260 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6317. Min Range: -2.6317
Max Act: 2.4703. Min Act: -0.1700
Data Index: 4279227 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6317. Min Range: -2.6317
Max Act: 2.4703. Min Act: -0.1700
Data Index: 5845766 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6317. Min Range: -2.6317
Max Act: 2.4703. Min Act: -0.1698
Data Index: 1804438 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6317. Min Range: -2.6317
Max Act: 2.4540. Min Act: -0.1700
Data Index: 6590002 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6317. Min Range: -2.6317
Max Act: 2.4540. Min Act: -0.1700
Data Index: 8032065 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #19