Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4279 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6073. Min Range: -2.6073
Max Act: 2.6073. Min Act: -0.1700
Data Index: 2095871 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6073. Min Range: -2.6073
Max Act: 2.5429. Min Act: -0.1700
Data Index: 8630847 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6073. Min Range: -2.6073
Max Act: 2.5105. Min Act: -0.1700
Data Index: 8316681 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6073. Min Range: -2.6073
Max Act: 2.4943. Min Act: -0.1700
Data Index: 6238919 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6073. Min Range: -2.6073
Max Act: 2.4781. Min Act: -0.1700
Data Index: 8562606 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6073. Min Range: -2.6073
Max Act: 2.4781. Min Act: -0.1700
Data Index: 6082831 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6073. Min Range: -2.6073
Max Act: 2.4781. Min Act: -0.1700
Data Index: 4940135 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6073. Min Range: -2.6073
Max Act: 2.4619. Min Act: -0.1700
Data Index: 5208170 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6073. Min Range: -2.6073
Max Act: 2.4619. Min Act: -0.1700
Data Index: 5688942 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6073. Min Range: -2.6073
Max Act: 2.4619. Min Act: -0.1700
Data Index: 5483417 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6073. Min Range: -2.6073
Max Act: 2.4781. Min Act: -0.1700
Data Index: 7305346 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6073. Min Range: -2.6073
Max Act: 2.4619. Min Act: -0.1700
Data Index: 6475674 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6073. Min Range: -2.6073
Max Act: 2.4619. Min Act: -0.1700
Data Index: 5287545 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6073. Min Range: -2.6073
Max Act: 2.4456. Min Act: -0.1700
Data Index: 8097203 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6073. Min Range: -2.6073
Max Act: 2.4293. Min Act: -0.1700
Data Index: 3267417 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6073. Min Range: -2.6073
Max Act: 2.4293. Min Act: -0.1700
Data Index: 5388497 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6073. Min Range: -2.6073
Max Act: 2.4131. Min Act: -0.1700
Data Index: 7778209 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6073. Min Range: -2.6073
Max Act: 2.4131. Min Act: -0.1700
Data Index: 7981841 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6073. Min Range: -2.6073
Max Act: 2.3967. Min Act: -0.1700
Data Index: 3556654 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6073. Min Range: -2.6073
Max Act: 2.4131. Min Act: -0.1700
Data Index: 2159205 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #19