Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1793 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.8684. Min Act: -0.1700
Data Index: 6939846 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.8059. Min Act: -0.1700
Data Index: 8062413 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.7434. Min Act: -0.1700
Data Index: 1681023 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.6809. Min Act: -0.1700
Data Index: 3076124 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.6184. Min Act: -0.1700
Data Index: 1549287 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.5559. Min Act: -0.1700
Data Index: 1911341 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.5559. Min Act: -0.1700
Data Index: 1970188 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.5559. Min Act: -0.1700
Data Index: 5349377 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.4934. Min Act: -0.1700
Data Index: 3482010 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.4934. Min Act: -0.1700
Data Index: 6259263 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.4934. Min Act: -0.1700
Data Index: 6355580 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.4309. Min Act: -0.1700
Data Index: 7338934 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.4309. Min Act: -0.1700
Data Index: 8137494 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.4309. Min Act: -0.1700
Data Index: 7646741 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.3996. Min Act: -0.1700
Data Index: 6657991 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.3996. Min Act: -0.1700
Data Index: 1322391 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.3684. Min Act: -0.1700
Data Index: 4855595 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.3684. Min Act: -0.1700
Data Index: 3011007 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.3371. Min Act: -0.1700
Data Index: 4692935 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.3059. Min Act: -0.1700
Data Index: 4384333 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19