Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3204 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.9044. Min Act: -0.1700
Data Index: 6415269 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.6232. Min Act: -0.1700
Data Index: 2527295 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.6544. Min Act: -0.1700
Data Index: 281373 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.5919. Min Act: -0.1700
Data Index: 7591054 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.5294. Min Act: -0.1700
Data Index: 4296333 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.5294. Min Act: -0.1700
Data Index: 1084600 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.5294. Min Act: -0.1700
Data Index: 5353472 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.4982. Min Act: -0.1700
Data Index: 2449222 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.4982. Min Act: -0.1700
Data Index: 7867896 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.4982. Min Act: -0.1700
Data Index: 1319530 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.4669. Min Act: -0.1700
Data Index: 8565191 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.4982. Min Act: -0.1700
Data Index: 5598034 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.4669. Min Act: -0.1700
Data Index: 737887 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.4669. Min Act: -0.1700
Data Index: 4198878 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.4669. Min Act: -0.1700
Data Index: 6650134 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.4669. Min Act: -0.1700
Data Index: 7583018 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.4357. Min Act: -0.1700
Data Index: 2902261 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.4357. Min Act: -0.1700
Data Index: 2200852 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.4044. Min Act: -0.1700
Data Index: 7182034 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.3732. Min Act: -0.1700
Data Index: 1658586 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #19