Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2570 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.9881. Min Act: -0.1700
Data Index: 5975913 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.9881. Min Act: -0.1700
Data Index: 7123191 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.9256. Min Act: -0.1700
Data Index: 4541693 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.8943. Min Act: -0.1700
Data Index: 918887 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.8943. Min Act: -0.1700
Data Index: 8238780 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.8318. Min Act: -0.1700
Data Index: 5423027 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.8006. Min Act: -0.1700
Data Index: 1234003 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.8006. Min Act: -0.1700
Data Index: 6562108 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.7693. Min Act: -0.1700
Data Index: 768392 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.7693. Min Act: -0.1700
Data Index: 3981456 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.7693. Min Act: -0.1700
Data Index: 518369 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.7381. Min Act: -0.1700
Data Index: 6102813 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.7068. Min Act: -0.1700
Data Index: 3523705 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.7068. Min Act: -0.1700
Data Index: 3071060 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.7068. Min Act: -0.1700
Data Index: 4198707 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.7068. Min Act: -0.1700
Data Index: 6638430 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.6756. Min Act: -0.1700
Data Index: 6815282 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.6756. Min Act: -0.1700
Data Index: 3643153 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.6756. Min Act: -0.1700
Data Index: 331582 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.6756. Min Act: -0.1700
Data Index: 7519586 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #19