Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2377 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3632. Min Range: -5.3632
Max Act: 5.3632. Min Act: -0.1700
Data Index: 7282319 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3632. Min Range: -5.3632
Max Act: 5.3007. Min Act: -0.1700
Data Index: 3516901 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3632. Min Range: -5.3632
Max Act: 5.3007. Min Act: -0.1700
Data Index: 1523089 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3632. Min Range: -5.3632
Max Act: 5.2695. Min Act: -0.1700
Data Index: 5582235 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3632. Min Range: -5.3632
Max Act: 5.2382. Min Act: -0.1700
Data Index: 524878 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3632. Min Range: -5.3632
Max Act: 5.2382. Min Act: -0.1700
Data Index: 56118 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3632. Min Range: -5.3632
Max Act: 5.2382. Min Act: -0.1700
Data Index: 347999 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3632. Min Range: -5.3632
Max Act: 5.2382. Min Act: -0.1700
Data Index: 2601476 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3632. Min Range: -5.3632
Max Act: 5.2070. Min Act: -0.1700
Data Index: 8497414 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3632. Min Range: -5.3632
Max Act: 5.2382. Min Act: -0.1700
Data Index: 5255392 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3632. Min Range: -5.3632
Max Act: 5.2070. Min Act: -0.1700
Data Index: 3776826 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3632. Min Range: -5.3632
Max Act: 5.2070. Min Act: -0.1700
Data Index: 292929 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3632. Min Range: -5.3632
Max Act: 5.1757. Min Act: -0.1700
Data Index: 2936581 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3632. Min Range: -5.3632
Max Act: 5.1757. Min Act: -0.1700
Data Index: 8216908 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3632. Min Range: -5.3632
Max Act: 5.1757. Min Act: -0.1700
Data Index: 1644072 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3632. Min Range: -5.3632
Max Act: 5.1757. Min Act: -0.1700
Data Index: 7874629 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3632. Min Range: -5.3632
Max Act: 5.1757. Min Act: -0.1700
Data Index: 1851442 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3632. Min Range: -5.3632
Max Act: 5.1757. Min Act: -0.1700
Data Index: 5977430 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3632. Min Range: -5.3632
Max Act: 5.1757. Min Act: -0.1700
Data Index: 6841095 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3632. Min Range: -5.3632
Max Act: 5.1757. Min Act: -0.1700
Data Index: 1184345 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19