Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4911 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.7471. Min Range: -1.7471
Max Act: 1.7471. Min Act: -0.1700
Data Index: 322417 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7471. Min Range: -1.7471
Max Act: 1.6256. Min Act: -0.1700
Data Index: 7867437 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7471. Min Range: -1.7471
Max Act: 1.5557. Min Act: -0.1700
Data Index: 3976413 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7471. Min Range: -1.7471
Max Act: 1.5557. Min Act: -0.1700
Data Index: 3578932 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7471. Min Range: -1.7471
Max Act: 1.5557. Min Act: -0.1700
Data Index: 8788860 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7471. Min Range: -1.7471
Max Act: 1.5557. Min Act: -0.1700
Data Index: 2700136 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7471. Min Range: -1.7471
Max Act: 1.5382. Min Act: -0.1700
Data Index: 6311855 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7471. Min Range: -1.7471
Max Act: 1.5382. Min Act: -0.1700
Data Index: 315088 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7471. Min Range: -1.7471
Max Act: 1.5382. Min Act: -0.1700
Data Index: 1716856 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7471. Min Range: -1.7471
Max Act: 1.5206. Min Act: -0.1700
Data Index: 6198981 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7471. Min Range: -1.7471
Max Act: 1.5382. Min Act: -0.1700
Data Index: 1581339 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7471. Min Range: -1.7471
Max Act: 1.5119. Min Act: -0.1700
Data Index: 7754178 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7471. Min Range: -1.7471
Max Act: 1.5119. Min Act: -0.1700
Data Index: 4214085 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7471. Min Range: -1.7471
Max Act: 1.5031. Min Act: -0.1700
Data Index: 3918478 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7471. Min Range: -1.7471
Max Act: 1.4855. Min Act: -0.1700
Data Index: 1458148 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7471. Min Range: -1.7471
Max Act: 1.4943. Min Act: -0.1700
Data Index: 1380015 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7471. Min Range: -1.7471
Max Act: 1.4943. Min Act: -0.1700
Data Index: 2823799 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7471. Min Range: -1.7471
Max Act: 1.5031. Min Act: -0.1700
Data Index: 3225408 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7471. Min Range: -1.7471
Max Act: 1.4855. Min Act: -0.1700
Data Index: 3001141 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7471. Min Range: -1.7471
Max Act: 1.4943. Min Act: -0.1700
Data Index: 3098410 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19