Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1916 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8904. Min Range: -3.8904
Max Act: 3.8904. Min Act: -0.1700
Data Index: 3165883 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8904. Min Range: -3.8904
Max Act: 3.8904. Min Act: -0.1700
Data Index: 7355572 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8904. Min Range: -3.8904
Max Act: 3.8592. Min Act: -0.1700
Data Index: 1696454 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8904. Min Range: -3.8904
Max Act: 3.8279. Min Act: -0.1700
Data Index: 6751257 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8904. Min Range: -3.8904
Max Act: 3.8279. Min Act: -0.1700
Data Index: 281953 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8904. Min Range: -3.8904
Max Act: 3.7966. Min Act: -0.1700
Data Index: 5199290 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8904. Min Range: -3.8904
Max Act: 3.7810. Min Act: -0.1700
Data Index: 1988311 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8904. Min Range: -3.8904
Max Act: 3.7810. Min Act: -0.1700
Data Index: 6448538 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8904. Min Range: -3.8904
Max Act: 3.7654. Min Act: -0.1700
Data Index: 4856578 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8904. Min Range: -3.8904
Max Act: 3.7966. Min Act: -0.1700
Data Index: 2316020 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8904. Min Range: -3.8904
Max Act: 3.7810. Min Act: -0.1700
Data Index: 774542 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8904. Min Range: -3.8904
Max Act: 3.7810. Min Act: -0.1700
Data Index: 2656151 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8904. Min Range: -3.8904
Max Act: 3.7654. Min Act: -0.1700
Data Index: 1169851 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8904. Min Range: -3.8904
Max Act: 3.7810. Min Act: -0.1700
Data Index: 1811102 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8904. Min Range: -3.8904
Max Act: 3.7497. Min Act: -0.1700
Data Index: 8352688 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8904. Min Range: -3.8904
Max Act: 3.7341. Min Act: -0.1700
Data Index: 827927 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8904. Min Range: -3.8904
Max Act: 3.7654. Min Act: -0.1700
Data Index: 8440576 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8904. Min Range: -3.8904
Max Act: 3.7184. Min Act: -0.1700
Data Index: 5201230 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8904. Min Range: -3.8904
Max Act: 3.7654. Min Act: -0.1700
Data Index: 5208271 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8904. Min Range: -3.8904
Max Act: 3.7184. Min Act: -0.1700
Data Index: 437179 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19