Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2082 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0533. Min Range: -6.0533
Max Act: 6.0533. Min Act: -0.1700
Data Index: 4802493 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0533. Min Range: -6.0533
Max Act: 5.9595. Min Act: -0.1700
Data Index: 5444663 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0533. Min Range: -6.0533
Max Act: 5.8970. Min Act: -0.1700
Data Index: 4789389 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0533. Min Range: -6.0533
Max Act: 5.8970. Min Act: -0.1700
Data Index: 4146659 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0533. Min Range: -6.0533
Max Act: 5.8658. Min Act: -0.1700
Data Index: 4775915 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0533. Min Range: -6.0533
Max Act: 5.8033. Min Act: -0.1700
Data Index: 5016512 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0533. Min Range: -6.0533
Max Act: 5.8345. Min Act: -0.1700
Data Index: 1842254 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0533. Min Range: -6.0533
Max Act: 5.8033. Min Act: -0.1700
Data Index: 5279373 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0533. Min Range: -6.0533
Max Act: 5.7720. Min Act: -0.1700
Data Index: 8733039 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0533. Min Range: -6.0533
Max Act: 5.7408. Min Act: -0.1700
Data Index: 6801790 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0533. Min Range: -6.0533
Max Act: 5.7408. Min Act: -0.1700
Data Index: 4345082 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0533. Min Range: -6.0533
Max Act: 5.7408. Min Act: -0.1700
Data Index: 7853446 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0533. Min Range: -6.0533
Max Act: 5.7408. Min Act: -0.1700
Data Index: 2692848 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0533. Min Range: -6.0533
Max Act: 5.7408. Min Act: -0.1700
Data Index: 2248360 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0533. Min Range: -6.0533
Max Act: 5.7408. Min Act: -0.1700
Data Index: 8042418 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0533. Min Range: -6.0533
Max Act: 5.7095. Min Act: -0.1700
Data Index: 7676588 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0533. Min Range: -6.0533
Max Act: 5.7408. Min Act: -0.1700
Data Index: 3116660 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0533. Min Range: -6.0533
Max Act: 5.7095. Min Act: -0.1700
Data Index: 6474121 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0533. Min Range: -6.0533
Max Act: 5.6783. Min Act: -0.1700
Data Index: 4042285 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0533. Min Range: -6.0533
Max Act: 5.7095. Min Act: -0.1700
Data Index: 1147308 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #19