Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 340 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.9904. Min Act: -0.1700
Data Index: 1905524 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.9591. Min Act: -0.1700
Data Index: 4400520 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.9591. Min Act: -0.1700
Data Index: 4057294 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.9279. Min Act: -0.1700
Data Index: 7533722 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.8966. Min Act: -0.1700
Data Index: 3637586 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.8654. Min Act: -0.1700
Data Index: 4934036 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.8341. Min Act: -0.1700
Data Index: 5203772 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.8654. Min Act: -0.1700
Data Index: 1370895 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.8341. Min Act: -0.1700
Data Index: 744038 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.8341. Min Act: -0.1700
Data Index: 3673117 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.8029. Min Act: -0.1700
Data Index: 885423 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.8029. Min Act: -0.1700
Data Index: 6344052 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.8029. Min Act: -0.1700
Data Index: 3874533 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.8029. Min Act: -0.1700
Data Index: 8091281 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.8029. Min Act: -0.1700
Data Index: 1745412 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.8029. Min Act: -0.1700
Data Index: 1112744 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.7716. Min Act: -0.1700
Data Index: 3915786 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.7716. Min Act: -0.1700
Data Index: 6057974 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.7716. Min Act: -0.1700
Data Index: 1384733 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.7716. Min Act: -0.1700
Data Index: 6423844 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19