Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4577 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5976. Min Range: -6.5976
Max Act: 6.5976. Min Act: -0.1700
Data Index: 5597267 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5976. Min Range: -6.5976
Max Act: 6.5664. Min Act: -0.1700
Data Index: 1200533 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5976. Min Range: -6.5976
Max Act: 6.4726. Min Act: -0.1700
Data Index: 4562567 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5976. Min Range: -6.5976
Max Act: 6.4101. Min Act: -0.1700
Data Index: 7990922 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5976. Min Range: -6.5976
Max Act: 6.4101. Min Act: -0.1700
Data Index: 8019340 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5976. Min Range: -6.5976
Max Act: 6.3476. Min Act: -0.1700
Data Index: 3376568 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5976. Min Range: -6.5976
Max Act: 6.3789. Min Act: -0.1700
Data Index: 2200467 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5976. Min Range: -6.5976
Max Act: 6.3476. Min Act: -0.1700
Data Index: 4563819 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5976. Min Range: -6.5976
Max Act: 6.3164. Min Act: -0.1700
Data Index: 1201265 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5976. Min Range: -6.5976
Max Act: 6.2851. Min Act: -0.1700
Data Index: 1929067 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5976. Min Range: -6.5976
Max Act: 6.2539. Min Act: -0.1700
Data Index: 5493671 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5976. Min Range: -6.5976
Max Act: 6.2539. Min Act: -0.1700
Data Index: 4794349 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5976. Min Range: -6.5976
Max Act: 6.2226. Min Act: -0.1700
Data Index: 7433649 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5976. Min Range: -6.5976
Max Act: 6.2226. Min Act: -0.1700
Data Index: 4794351 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5976. Min Range: -6.5976
Max Act: 6.2226. Min Act: -0.1700
Data Index: 7802806 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5976. Min Range: -6.5976
Max Act: 6.2226. Min Act: -0.1700
Data Index: 4445270 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5976. Min Range: -6.5976
Max Act: 6.1601. Min Act: -0.1700
Data Index: 2418114 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5976. Min Range: -6.5976
Max Act: 6.1601. Min Act: -0.1700
Data Index: 33859 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5976. Min Range: -6.5976
Max Act: 6.1601. Min Act: -0.1700
Data Index: 3272864 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5976. Min Range: -6.5976
Max Act: 6.1601. Min Act: -0.1700
Data Index: 1031899 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #19