Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3291 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2598. Min Range: -7.2598
Max Act: 7.2598. Min Act: -0.1700
Data Index: 3907457 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2598. Min Range: -7.2598
Max Act: 7.2286. Min Act: -0.1700
Data Index: 5258669 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2598. Min Range: -7.2598
Max Act: 7.1661. Min Act: -0.1700
Data Index: 1348713 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2598. Min Range: -7.2598
Max Act: 7.1973. Min Act: -0.1700
Data Index: 2864588 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2598. Min Range: -7.2598
Max Act: 7.1348. Min Act: -0.1700
Data Index: 4651296 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2598. Min Range: -7.2598
Max Act: 7.1661. Min Act: -0.1700
Data Index: 6734133 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2598. Min Range: -7.2598
Max Act: 7.1661. Min Act: -0.1700
Data Index: 6090824 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2598. Min Range: -7.2598
Max Act: 7.1348. Min Act: -0.1700
Data Index: 7095874 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2598. Min Range: -7.2598
Max Act: 7.0723. Min Act: -0.1700
Data Index: 8156410 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2598. Min Range: -7.2598
Max Act: 7.0411. Min Act: -0.1700
Data Index: 1288038 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2598. Min Range: -7.2598
Max Act: 7.0411. Min Act: -0.1700
Data Index: 333048 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2598. Min Range: -7.2598
Max Act: 7.0411. Min Act: -0.1700
Data Index: 6913670 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2598. Min Range: -7.2598
Max Act: 7.0098. Min Act: -0.1700
Data Index: 5050220 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2598. Min Range: -7.2598
Max Act: 6.9786. Min Act: -0.1700
Data Index: 5830435 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2598. Min Range: -7.2598
Max Act: 7.0098. Min Act: -0.1700
Data Index: 746901 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2598. Min Range: -7.2598
Max Act: 6.9786. Min Act: -0.1700
Data Index: 7922156 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2598. Min Range: -7.2598
Max Act: 6.9473. Min Act: -0.1700
Data Index: 3194344 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2598. Min Range: -7.2598
Max Act: 6.9786. Min Act: -0.1700
Data Index: 8073547 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2598. Min Range: -7.2598
Max Act: 7.0098. Min Act: -0.1700
Data Index: 7840642 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2598. Min Range: -7.2598
Max Act: 6.9786. Min Act: -0.1700
Data Index: 3010191 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19