Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3390 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8044. Min Range: -7.8044
Max Act: 7.8044. Min Act: -0.1700
Data Index: 5344880 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8044. Min Range: -7.8044
Max Act: 7.4606. Min Act: -0.1700
Data Index: 7322354 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8044. Min Range: -7.8044
Max Act: 7.4294. Min Act: -0.1700
Data Index: 3737158 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8044. Min Range: -7.8044
Max Act: 7.4294. Min Act: -0.1700
Data Index: 2458283 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8044. Min Range: -7.8044
Max Act: 7.4294. Min Act: -0.1700
Data Index: 573349 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8044. Min Range: -7.8044
Max Act: 7.4294. Min Act: -0.1700
Data Index: 569316 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8044. Min Range: -7.8044
Max Act: 7.3669. Min Act: -0.1700
Data Index: 899525 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8044. Min Range: -7.8044
Max Act: 7.3669. Min Act: -0.1700
Data Index: 3847148 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8044. Min Range: -7.8044
Max Act: 7.3356. Min Act: -0.1700
Data Index: 217571 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8044. Min Range: -7.8044
Max Act: 7.3356. Min Act: -0.1700
Data Index: 3302099 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8044. Min Range: -7.8044
Max Act: 7.3356. Min Act: -0.1700
Data Index: 4088313 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8044. Min Range: -7.8044
Max Act: 7.3356. Min Act: -0.1700
Data Index: 4082795 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8044. Min Range: -7.8044
Max Act: 7.3044. Min Act: -0.1700
Data Index: 1438004 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8044. Min Range: -7.8044
Max Act: 7.2731. Min Act: -0.1700
Data Index: 972169 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8044. Min Range: -7.8044
Max Act: 7.2731. Min Act: -0.1700
Data Index: 3033608 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8044. Min Range: -7.8044
Max Act: 7.3044. Min Act: -0.1700
Data Index: 4467890 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8044. Min Range: -7.8044
Max Act: 7.2419. Min Act: -0.1700
Data Index: 5246233 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8044. Min Range: -7.8044
Max Act: 7.2419. Min Act: -0.1700
Data Index: 536609 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8044. Min Range: -7.8044
Max Act: 7.2419. Min Act: -0.1700
Data Index: 4651618 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8044. Min Range: -7.8044
Max Act: 7.2419. Min Act: -0.1700
Data Index: 7205551 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19