Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3038 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9898. Min Range: -3.9898
Max Act: 3.9898. Min Act: -0.1700
Data Index: 5685327 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9898. Min Range: -3.9898
Max Act: 3.8648. Min Act: -0.1700
Data Index: 1430170 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9898. Min Range: -3.9898
Max Act: 3.7866. Min Act: -0.1700
Data Index: 88570 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9898. Min Range: -3.9898
Max Act: 3.7866. Min Act: -0.1700
Data Index: 1752421 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9898. Min Range: -3.9898
Max Act: 3.7397. Min Act: -0.1700
Data Index: 6141205 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9898. Min Range: -3.9898
Max Act: 3.7084. Min Act: -0.1700
Data Index: 7285158 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9898. Min Range: -3.9898
Max Act: 3.7084. Min Act: -0.1700
Data Index: 1998633 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9898. Min Range: -3.9898
Max Act: 3.7084. Min Act: -0.1700
Data Index: 5078139 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9898. Min Range: -3.9898
Max Act: 3.7240. Min Act: -0.1700
Data Index: 142593 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9898. Min Range: -3.9898
Max Act: 3.6927. Min Act: -0.1700
Data Index: 44461 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9898. Min Range: -3.9898
Max Act: 3.6927. Min Act: -0.1700
Data Index: 4303752 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9898. Min Range: -3.9898
Max Act: 3.6771. Min Act: -0.1700
Data Index: 5569273 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9898. Min Range: -3.9898
Max Act: 3.6771. Min Act: -0.1700
Data Index: 1911489 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9898. Min Range: -3.9898
Max Act: 3.6614. Min Act: -0.1700
Data Index: 6986570 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9898. Min Range: -3.9898
Max Act: 3.6614. Min Act: -0.1700
Data Index: 1562888 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9898. Min Range: -3.9898
Max Act: 3.6614. Min Act: -0.1700
Data Index: 5644867 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9898. Min Range: -3.9898
Max Act: 3.6614. Min Act: -0.1700
Data Index: 6083192 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9898. Min Range: -3.9898
Max Act: 3.6458. Min Act: -0.1700
Data Index: 5954964 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9898. Min Range: -3.9898
Max Act: 3.6458. Min Act: -0.1700
Data Index: 1998634 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9898. Min Range: -3.9898
Max Act: 3.6458. Min Act: -0.1700
Data Index: 4711133 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19