Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4496 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5080. Min Range: -3.5080
Max Act: 3.5080. Min Act: -0.1700
Data Index: 8158601 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5080. Min Range: -3.5080
Max Act: 3.1627. Min Act: -0.1700
Data Index: 1731118 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5080. Min Range: -3.5080
Max Act: 3.1470. Min Act: -0.1700
Data Index: 2570300 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5080. Min Range: -3.5080
Max Act: 3.1155. Min Act: -0.1700
Data Index: 1552527 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5080. Min Range: -3.5080
Max Act: 3.0682. Min Act: -0.1700
Data Index: 7025260 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5080. Min Range: -3.5080
Max Act: 3.0524. Min Act: -0.1700
Data Index: 4213085 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5080. Min Range: -3.5080
Max Act: 3.0367. Min Act: -0.1700
Data Index: 5917040 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5080. Min Range: -3.5080
Max Act: 3.0209. Min Act: -0.1700
Data Index: 2342833 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5080. Min Range: -3.5080
Max Act: 3.0209. Min Act: -0.1700
Data Index: 8809825 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5080. Min Range: -3.5080
Max Act: 3.0209. Min Act: -0.1700
Data Index: 8208128 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5080. Min Range: -3.5080
Max Act: 2.9893. Min Act: -0.1700
Data Index: 1221378 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5080. Min Range: -3.5080
Max Act: 3.0051. Min Act: -0.1700
Data Index: 1804498 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5080. Min Range: -3.5080
Max Act: 2.9734. Min Act: -0.1700
Data Index: 3616437 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5080. Min Range: -3.5080
Max Act: 2.9576. Min Act: -0.1700
Data Index: 5424615 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5080. Min Range: -3.5080
Max Act: 2.9734. Min Act: -0.1700
Data Index: 4711159 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5080. Min Range: -3.5080
Max Act: 2.9576. Min Act: -0.1700
Data Index: 1413821 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5080. Min Range: -3.5080
Max Act: 2.9418. Min Act: -0.1700
Data Index: 7926505 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5080. Min Range: -3.5080
Max Act: 2.9576. Min Act: -0.1700
Data Index: 1050118 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5080. Min Range: -3.5080
Max Act: 2.9576. Min Act: -0.1700
Data Index: 834837 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5080. Min Range: -3.5080
Max Act: 2.9734. Min Act: -0.1700
Data Index: 7370022 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19