Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4106 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4479. Min Range: -4.4479
Max Act: 4.4479. Min Act: -0.1700
Data Index: 6052877 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4479. Min Range: -4.4479
Max Act: 4.4479. Min Act: -0.1700
Data Index: 5843825 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4479. Min Range: -4.4479
Max Act: 4.4167. Min Act: -0.1700
Data Index: 3339585 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4479. Min Range: -4.4479
Max Act: 4.3542. Min Act: -0.1700
Data Index: 5309914 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4479. Min Range: -4.4479
Max Act: 4.3854. Min Act: -0.1700
Data Index: 4992146 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4479. Min Range: -4.4479
Max Act: 4.3229. Min Act: -0.1700
Data Index: 5810593 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4479. Min Range: -4.4479
Max Act: 4.3542. Min Act: -0.1700
Data Index: 6929106 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4479. Min Range: -4.4479
Max Act: 4.2917. Min Act: -0.1700
Data Index: 4221266 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4479. Min Range: -4.4479
Max Act: 4.2604. Min Act: -0.1700
Data Index: 4594657 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4479. Min Range: -4.4479
Max Act: 4.2604. Min Act: -0.1700
Data Index: 2217390 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4479. Min Range: -4.4479
Max Act: 4.2604. Min Act: -0.1700
Data Index: 8599731 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4479. Min Range: -4.4479
Max Act: 4.2604. Min Act: -0.1700
Data Index: 4699993 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4479. Min Range: -4.4479
Max Act: 4.2604. Min Act: -0.1700
Data Index: 8654508 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4479. Min Range: -4.4479
Max Act: 4.2604. Min Act: -0.1700
Data Index: 6673323 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4479. Min Range: -4.4479
Max Act: 4.2604. Min Act: -0.1700
Data Index: 6189576 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4479. Min Range: -4.4479
Max Act: 4.2604. Min Act: -0.1700
Data Index: 5168814 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4479. Min Range: -4.4479
Max Act: 4.2604. Min Act: -0.1700
Data Index: 4757905 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4479. Min Range: -4.4479
Max Act: 4.2292. Min Act: -0.1700
Data Index: 2139865 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4479. Min Range: -4.4479
Max Act: 4.2292. Min Act: -0.1700
Data Index: 6174582 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4479. Min Range: -4.4479
Max Act: 4.1979. Min Act: -0.1700
Data Index: 6556875 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19