Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1348 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.2093. Min Range: -7.2093
Max Act: 7.2093. Min Act: -0.1700
Data Index: 289912 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2093. Min Range: -7.2093
Max Act: 7.0218. Min Act: -0.1700
Data Index: 1502285 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2093. Min Range: -7.2093
Max Act: 6.9593. Min Act: -0.1700
Data Index: 4386852 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2093. Min Range: -7.2093
Max Act: 7.0218. Min Act: -0.1700
Data Index: 1156707 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2093. Min Range: -7.2093
Max Act: 6.7718. Min Act: -0.1700
Data Index: 5660685 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2093. Min Range: -7.2093
Max Act: 6.6781. Min Act: -0.1700
Data Index: 6067616 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2093. Min Range: -7.2093
Max Act: 6.6156. Min Act: -0.1700
Data Index: 1885251 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2093. Min Range: -7.2093
Max Act: 6.5531. Min Act: -0.1700
Data Index: 4882749 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2093. Min Range: -7.2093
Max Act: 6.6156. Min Act: -0.1700
Data Index: 8334663 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2093. Min Range: -7.2093
Max Act: 6.5843. Min Act: -0.1700
Data Index: 6746721 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2093. Min Range: -7.2093
Max Act: 6.5843. Min Act: -0.1700
Data Index: 7469180 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2093. Min Range: -7.2093
Max Act: 6.5531. Min Act: -0.1700
Data Index: 1819345 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2093. Min Range: -7.2093
Max Act: 6.5218. Min Act: -0.1700
Data Index: 6527635 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2093. Min Range: -7.2093
Max Act: 6.4906. Min Act: -0.1700
Data Index: 312185 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2093. Min Range: -7.2093
Max Act: 6.4906. Min Act: -0.1700
Data Index: 4377324 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2093. Min Range: -7.2093
Max Act: 6.4593. Min Act: -0.1700
Data Index: 8006611 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2093. Min Range: -7.2093
Max Act: 6.4593. Min Act: -0.1700
Data Index: 6637802 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2093. Min Range: -7.2093
Max Act: 6.3968. Min Act: -0.1700
Data Index: 3173406 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2093. Min Range: -7.2093
Max Act: 6.3968. Min Act: -0.1700
Data Index: 2449066 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2093. Min Range: -7.2093
Max Act: 6.3968. Min Act: -0.1700
Data Index: 2237735 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19