Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2508 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2702. Min Range: -7.2702
Max Act: 7.2702. Min Act: -0.1700
Data Index: 3020953 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2702. Min Range: -7.2702
Max Act: 7.2390. Min Act: -0.1700
Data Index: 2742489 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2702. Min Range: -7.2702
Max Act: 7.1765. Min Act: -0.1700
Data Index: 3130066 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2702. Min Range: -7.2702
Max Act: 7.1765. Min Act: -0.1700
Data Index: 1792835 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2702. Min Range: -7.2702
Max Act: 7.1140. Min Act: -0.1700
Data Index: 5637966 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2702. Min Range: -7.2702
Max Act: 7.1765. Min Act: -0.1700
Data Index: 38483 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2702. Min Range: -7.2702
Max Act: 7.1452. Min Act: -0.1700
Data Index: 5088245 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2702. Min Range: -7.2702
Max Act: 7.1452. Min Act: -0.1700
Data Index: 2528483 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2702. Min Range: -7.2702
Max Act: 7.1452. Min Act: -0.1700
Data Index: 623453 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2702. Min Range: -7.2702
Max Act: 7.0827. Min Act: -0.1700
Data Index: 2253408 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2702. Min Range: -7.2702
Max Act: 7.0515. Min Act: -0.1700
Data Index: 2476867 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2702. Min Range: -7.2702
Max Act: 7.0515. Min Act: -0.1700
Data Index: 7740551 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2702. Min Range: -7.2702
Max Act: 6.9890. Min Act: -0.1700
Data Index: 8096255 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2702. Min Range: -7.2702
Max Act: 6.9890. Min Act: -0.1700
Data Index: 8056833 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2702. Min Range: -7.2702
Max Act: 6.9577. Min Act: -0.1700
Data Index: 1545754 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2702. Min Range: -7.2702
Max Act: 6.9577. Min Act: -0.1700
Data Index: 4109420 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2702. Min Range: -7.2702
Max Act: 6.9577. Min Act: -0.1700
Data Index: 7281595 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2702. Min Range: -7.2702
Max Act: 6.9577. Min Act: -0.1700
Data Index: 6201281 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2702. Min Range: -7.2702
Max Act: 6.8952. Min Act: -0.1700
Data Index: 7250954 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2702. Min Range: -7.2702
Max Act: 6.9265. Min Act: -0.1700
Data Index: 448522 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19