Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4371 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.5145. Min Act: -0.1700
Data Index: 6193298 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.3270. Min Act: -0.1700
Data Index: 6238131 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.2645. Min Act: -0.1700
Data Index: 2816896 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.2020. Min Act: -0.1700
Data Index: 2068967 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.2020. Min Act: -0.1700
Data Index: 2568181 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.1708. Min Act: -0.1700
Data Index: 3125335 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.2020. Min Act: -0.1700
Data Index: 1754569 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.2020. Min Act: -0.1700
Data Index: 5356875 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.1083. Min Act: -0.1700
Data Index: 415988 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.1083. Min Act: -0.1700
Data Index: 5305286 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.1083. Min Act: -0.1700
Data Index: 3972534 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.1083. Min Act: -0.1700
Data Index: 3091443 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.0770. Min Act: -0.1700
Data Index: 1311079 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.0458. Min Act: -0.1700
Data Index: 7825586 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.0770. Min Act: -0.1700
Data Index: 4241897 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.0458. Min Act: -0.1700
Data Index: 7355671 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.0770. Min Act: -0.1700
Data Index: 6733534 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.0458. Min Act: -0.1700
Data Index: 5106349 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.0458. Min Act: -0.1700
Data Index: 7291127 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.0458. Min Act: -0.1700
Data Index: 4703698 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19