Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4416 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9074. Min Range: -8.9074
Max Act: 8.8449. Min Act: -0.1700
Data Index: 3420088 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9074. Min Range: -8.9074
Max Act: 8.9074. Min Act: -0.1700
Data Index: 3973715 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9074. Min Range: -8.9074
Max Act: 8.7824. Min Act: -0.1700
Data Index: 507361 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9074. Min Range: -8.9074
Max Act: 8.8449. Min Act: -0.1700
Data Index: 7164458 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9074. Min Range: -8.9074
Max Act: 8.7199. Min Act: -0.1700
Data Index: 6112508 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9074. Min Range: -8.9074
Max Act: 8.7199. Min Act: -0.1700
Data Index: 523296 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9074. Min Range: -8.9074
Max Act: 8.6574. Min Act: -0.1700
Data Index: 2945616 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9074. Min Range: -8.9074
Max Act: 8.6574. Min Act: -0.1700
Data Index: 5857996 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9074. Min Range: -8.9074
Max Act: 8.6574. Min Act: -0.1700
Data Index: 3827572 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9074. Min Range: -8.9074
Max Act: 8.5949. Min Act: -0.1700
Data Index: 1494423 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9074. Min Range: -8.9074
Max Act: 8.5324. Min Act: -0.1700
Data Index: 3261288 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9074. Min Range: -8.9074
Max Act: 8.4699. Min Act: -0.1700
Data Index: 4313374 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9074. Min Range: -8.9074
Max Act: 8.5949. Min Act: -0.1700
Data Index: 1691770 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9074. Min Range: -8.9074
Max Act: 8.5324. Min Act: -0.1700
Data Index: 3257883 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9074. Min Range: -8.9074
Max Act: 8.4699. Min Act: -0.1700
Data Index: 5488042 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9074. Min Range: -8.9074
Max Act: 8.5324. Min Act: -0.1700
Data Index: 7178121 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9074. Min Range: -8.9074
Max Act: 8.4699. Min Act: -0.1700
Data Index: 1336478 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9074. Min Range: -8.9074
Max Act: 8.5324. Min Act: -0.1700
Data Index: 4475709 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9074. Min Range: -8.9074
Max Act: 8.4699. Min Act: -0.1700
Data Index: 3219309 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9074. Min Range: -8.9074
Max Act: 8.4699. Min Act: -0.1700
Data Index: 1175051 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #19