Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2939 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4309. Min Range: -6.4309
Max Act: 6.4309. Min Act: -0.1700
Data Index: 3912543 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4309. Min Range: -6.4309
Max Act: 6.0871. Min Act: -0.1700
Data Index: 977741 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4309. Min Range: -6.4309
Max Act: 5.9309. Min Act: -0.1700
Data Index: 1930749 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4309. Min Range: -6.4309
Max Act: 5.9309. Min Act: -0.1700
Data Index: 5629145 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4309. Min Range: -6.4309
Max Act: 5.8996. Min Act: -0.1700
Data Index: 208811 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4309. Min Range: -6.4309
Max Act: 5.8684. Min Act: -0.1700
Data Index: 5591032 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4309. Min Range: -6.4309
Max Act: 5.8371. Min Act: -0.1700
Data Index: 3745881 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4309. Min Range: -6.4309
Max Act: 5.8371. Min Act: -0.1700
Data Index: 3257610 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4309. Min Range: -6.4309
Max Act: 5.8059. Min Act: -0.1700
Data Index: 7007466 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4309. Min Range: -6.4309
Max Act: 5.8059. Min Act: -0.1700
Data Index: 8341667 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4309. Min Range: -6.4309
Max Act: 5.7121. Min Act: -0.1700
Data Index: 3410972 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4309. Min Range: -6.4309
Max Act: 5.7121. Min Act: -0.1700
Data Index: 1324511 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4309. Min Range: -6.4309
Max Act: 5.7121. Min Act: -0.1700
Data Index: 3906657 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4309. Min Range: -6.4309
Max Act: 5.6809. Min Act: -0.1700
Data Index: 1732721 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4309. Min Range: -6.4309
Max Act: 5.6809. Min Act: -0.1700
Data Index: 8170706 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4309. Min Range: -6.4309
Max Act: 5.6809. Min Act: -0.1700
Data Index: 4526038 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4309. Min Range: -6.4309
Max Act: 5.6496. Min Act: -0.1700
Data Index: 4335325 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4309. Min Range: -6.4309
Max Act: 5.6496. Min Act: -0.1700
Data Index: 5871029 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4309. Min Range: -6.4309
Max Act: 5.6184. Min Act: -0.1700
Data Index: 5301765 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4309. Min Range: -6.4309
Max Act: 5.6184. Min Act: -0.1700
Data Index: 5425327 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19