Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2683 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2907. Min Range: -6.2907
Max Act: 6.2907. Min Act: -0.1700
Data Index: 7999705 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2907. Min Range: -6.2907
Max Act: 5.9782. Min Act: -0.1700
Data Index: 2941944 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2907. Min Range: -6.2907
Max Act: 5.9782. Min Act: -0.1700
Data Index: 1645906 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2907. Min Range: -6.2907
Max Act: 5.9157. Min Act: -0.1700
Data Index: 604771 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2907. Min Range: -6.2907
Max Act: 5.9469. Min Act: -0.1700
Data Index: 7252695 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2907. Min Range: -6.2907
Max Act: 5.8844. Min Act: -0.1700
Data Index: 2502521 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2907. Min Range: -6.2907
Max Act: 5.8844. Min Act: -0.1700
Data Index: 2157214 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2907. Min Range: -6.2907
Max Act: 5.8844. Min Act: -0.1700
Data Index: 5168676 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2907. Min Range: -6.2907
Max Act: 5.8532. Min Act: -0.1700
Data Index: 7114724 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2907. Min Range: -6.2907
Max Act: 5.8532. Min Act: -0.1700
Data Index: 2061199 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2907. Min Range: -6.2907
Max Act: 5.8219. Min Act: -0.1700
Data Index: 4842768 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2907. Min Range: -6.2907
Max Act: 5.8219. Min Act: -0.1700
Data Index: 8387260 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2907. Min Range: -6.2907
Max Act: 5.7907. Min Act: -0.1700
Data Index: 7928207 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2907. Min Range: -6.2907
Max Act: 5.7594. Min Act: -0.1700
Data Index: 6430308 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2907. Min Range: -6.2907
Max Act: 5.6969. Min Act: -0.1700
Data Index: 7937907 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2907. Min Range: -6.2907
Max Act: 5.6969. Min Act: -0.1700
Data Index: 4817673 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2907. Min Range: -6.2907
Max Act: 5.6969. Min Act: -0.1700
Data Index: 6236111 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2907. Min Range: -6.2907
Max Act: 5.6657. Min Act: -0.1700
Data Index: 1417706 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2907. Min Range: -6.2907
Max Act: 5.6657. Min Act: -0.1700
Data Index: 6036297 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2907. Min Range: -6.2907
Max Act: 5.6969. Min Act: -0.1700
Data Index: 5572595 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #19