Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3040 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9489. Min Range: -6.9489
Max Act: 6.9489. Min Act: -0.1700
Data Index: 2711378 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9489. Min Range: -6.9489
Max Act: 6.7301. Min Act: -0.1700
Data Index: 3706140 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9489. Min Range: -6.9489
Max Act: 6.6364. Min Act: -0.1700
Data Index: 7566947 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9489. Min Range: -6.9489
Max Act: 6.5739. Min Act: -0.1700
Data Index: 2784048 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9489. Min Range: -6.9489
Max Act: 6.4801. Min Act: -0.1700
Data Index: 515426 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9489. Min Range: -6.9489
Max Act: 6.4489. Min Act: -0.1700
Data Index: 1792240 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9489. Min Range: -6.9489
Max Act: 6.4489. Min Act: -0.1700
Data Index: 6217679 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9489. Min Range: -6.9489
Max Act: 6.4489. Min Act: -0.1700
Data Index: 4430773 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9489. Min Range: -6.9489
Max Act: 6.4801. Min Act: -0.1700
Data Index: 8334045 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9489. Min Range: -6.9489
Max Act: 6.4489. Min Act: -0.1700
Data Index: 6377370 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9489. Min Range: -6.9489
Max Act: 6.4176. Min Act: -0.1700
Data Index: 2106923 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9489. Min Range: -6.9489
Max Act: 6.4176. Min Act: -0.1700
Data Index: 6885814 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9489. Min Range: -6.9489
Max Act: 6.4176. Min Act: -0.1700
Data Index: 3251764 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9489. Min Range: -6.9489
Max Act: 6.3864. Min Act: -0.1700
Data Index: 8209899 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9489. Min Range: -6.9489
Max Act: 6.4176. Min Act: -0.1700
Data Index: 8137769 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9489. Min Range: -6.9489
Max Act: 6.4176. Min Act: -0.1700
Data Index: 3081473 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9489. Min Range: -6.9489
Max Act: 6.3864. Min Act: -0.1700
Data Index: 4616433 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9489. Min Range: -6.9489
Max Act: 6.3864. Min Act: -0.1700
Data Index: 8323389 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9489. Min Range: -6.9489
Max Act: 6.3551. Min Act: -0.1700
Data Index: 2517085 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9489. Min Range: -6.9489
Max Act: 6.2926. Min Act: -0.1700
Data Index: 4040785 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #19