Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2797 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2139. Min Range: -5.2139
Max Act: 5.2139. Min Act: -0.1700
Data Index: 8182150 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2139. Min Range: -5.2139
Max Act: 4.8702. Min Act: -0.1700
Data Index: 7405249 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2139. Min Range: -5.2139
Max Act: 4.9014. Min Act: -0.1700
Data Index: 8502097 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2139. Min Range: -5.2139
Max Act: 4.8702. Min Act: -0.1700
Data Index: 8083034 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2139. Min Range: -5.2139
Max Act: 4.8389. Min Act: -0.1700
Data Index: 1337173 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2139. Min Range: -5.2139
Max Act: 4.8389. Min Act: -0.1700
Data Index: 5848564 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2139. Min Range: -5.2139
Max Act: 4.8389. Min Act: -0.1700
Data Index: 6663176 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2139. Min Range: -5.2139
Max Act: 4.8077. Min Act: -0.1700
Data Index: 6380864 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2139. Min Range: -5.2139
Max Act: 4.8077. Min Act: -0.1700
Data Index: 6958191 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2139. Min Range: -5.2139
Max Act: 4.7764. Min Act: -0.1700
Data Index: 5992933 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2139. Min Range: -5.2139
Max Act: 4.7764. Min Act: -0.1700
Data Index: 4612944 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2139. Min Range: -5.2139
Max Act: 4.7764. Min Act: -0.1700
Data Index: 3210884 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2139. Min Range: -5.2139
Max Act: 4.7452. Min Act: -0.1700
Data Index: 8472544 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2139. Min Range: -5.2139
Max Act: 4.7139. Min Act: -0.1700
Data Index: 1337165 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2139. Min Range: -5.2139
Max Act: 4.7139. Min Act: -0.1700
Data Index: 2388696 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2139. Min Range: -5.2139
Max Act: 4.7139. Min Act: -0.1700
Data Index: 3237701 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2139. Min Range: -5.2139
Max Act: 4.6514. Min Act: -0.1700
Data Index: 2092854 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2139. Min Range: -5.2139
Max Act: 4.6827. Min Act: -0.1700
Data Index: 5388244 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2139. Min Range: -5.2139
Max Act: 4.6827. Min Act: -0.1700
Data Index: 8301377 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2139. Min Range: -5.2139
Max Act: 4.6514. Min Act: -0.1700
Data Index: 5230295 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19