Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4971 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7965. Min Range: -6.7965
Max Act: 6.7965. Min Act: -0.1700
Data Index: 4364228 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7965. Min Range: -6.7965
Max Act: 6.6715. Min Act: -0.1700
Data Index: 2935597 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7965. Min Range: -6.7965
Max Act: 6.6403. Min Act: -0.1700
Data Index: 8751406 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7965. Min Range: -6.7965
Max Act: 6.4215. Min Act: -0.1700
Data Index: 3041501 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7965. Min Range: -6.7965
Max Act: 6.4215. Min Act: -0.1700
Data Index: 7782904 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7965. Min Range: -6.7965
Max Act: 6.3278. Min Act: -0.1700
Data Index: 3971086 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7965. Min Range: -6.7965
Max Act: 6.2653. Min Act: -0.1700
Data Index: 1661846 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7965. Min Range: -6.7965
Max Act: 6.2340. Min Act: -0.1700
Data Index: 3950270 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7965. Min Range: -6.7965
Max Act: 6.2340. Min Act: -0.1700
Data Index: 8049091 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7965. Min Range: -6.7965
Max Act: 6.2028. Min Act: -0.1700
Data Index: 8761048 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7965. Min Range: -6.7965
Max Act: 6.2028. Min Act: -0.1700
Data Index: 113508 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7965. Min Range: -6.7965
Max Act: 6.2028. Min Act: -0.1700
Data Index: 8381042 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7965. Min Range: -6.7965
Max Act: 6.1715. Min Act: -0.1700
Data Index: 8072522 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7965. Min Range: -6.7965
Max Act: 6.1403. Min Act: -0.1700
Data Index: 3718290 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7965. Min Range: -6.7965
Max Act: 6.1715. Min Act: -0.1700
Data Index: 8034864 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7965. Min Range: -6.7965
Max Act: 6.1715. Min Act: -0.1700
Data Index: 4924918 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7965. Min Range: -6.7965
Max Act: 6.1403. Min Act: -0.1700
Data Index: 84228 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7965. Min Range: -6.7965
Max Act: 6.1403. Min Act: -0.1700
Data Index: 4430508 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7965. Min Range: -6.7965
Max Act: 6.1090. Min Act: -0.1700
Data Index: 802912 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7965. Min Range: -6.7965
Max Act: 6.1090. Min Act: -0.1700
Data Index: 3350568 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19