Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5556 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5777. Min Range: -7.5777
Max Act: 7.5777. Min Act: -0.1700
Data Index: 6908925 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5777. Min Range: -7.5777
Max Act: 7.5152. Min Act: -0.1700
Data Index: 3953875 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5777. Min Range: -7.5777
Max Act: 7.4527. Min Act: -0.1700
Data Index: 41605 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5777. Min Range: -7.5777
Max Act: 7.4527. Min Act: -0.1700
Data Index: 2290789 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5777. Min Range: -7.5777
Max Act: 7.4215. Min Act: -0.1700
Data Index: 1335997 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5777. Min Range: -7.5777
Max Act: 7.4215. Min Act: -0.1700
Data Index: 2272862 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5777. Min Range: -7.5777
Max Act: 7.3277. Min Act: -0.1700
Data Index: 8111196 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5777. Min Range: -7.5777
Max Act: 7.3590. Min Act: -0.1700
Data Index: 2944098 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5777. Min Range: -7.5777
Max Act: 7.3590. Min Act: -0.1700
Data Index: 1636034 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5777. Min Range: -7.5777
Max Act: 7.2965. Min Act: -0.1700
Data Index: 8091325 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5777. Min Range: -7.5777
Max Act: 7.2652. Min Act: -0.1700
Data Index: 886525 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5777. Min Range: -7.5777
Max Act: 7.2340. Min Act: -0.1700
Data Index: 4678424 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5777. Min Range: -7.5777
Max Act: 7.2340. Min Act: -0.1700
Data Index: 4283931 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5777. Min Range: -7.5777
Max Act: 7.2340. Min Act: -0.1700
Data Index: 713620 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5777. Min Range: -7.5777
Max Act: 7.2340. Min Act: -0.1700
Data Index: 3933027 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5777. Min Range: -7.5777
Max Act: 7.2027. Min Act: -0.1700
Data Index: 1756654 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5777. Min Range: -7.5777
Max Act: 7.2027. Min Act: -0.1700
Data Index: 914454 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5777. Min Range: -7.5777
Max Act: 7.2027. Min Act: -0.1700
Data Index: 6268945 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5777. Min Range: -7.5777
Max Act: 7.2340. Min Act: -0.1700
Data Index: 2588411 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5777. Min Range: -7.5777
Max Act: 7.2027. Min Act: -0.1700
Data Index: 2330232 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19