Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3112 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.8557. Min Act: -0.1700
Data Index: 2097875 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.6057. Min Act: -0.1700
Data Index: 4252410 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.4807. Min Act: -0.1700
Data Index: 3920480 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.4182. Min Act: -0.1700
Data Index: 4285112 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.4182. Min Act: -0.1700
Data Index: 8061698 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.4182. Min Act: -0.1700
Data Index: 5816680 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.3869. Min Act: -0.1700
Data Index: 5365896 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.3557. Min Act: -0.1700
Data Index: 1897154 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.3557. Min Act: -0.1700
Data Index: 1497291 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.3244. Min Act: -0.1700
Data Index: 3579512 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.3244. Min Act: -0.1700
Data Index: 2726651 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.3244. Min Act: -0.1700
Data Index: 8486503 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.3244. Min Act: -0.1700
Data Index: 4913321 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.2932. Min Act: -0.1700
Data Index: 384794 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.2619. Min Act: -0.1700
Data Index: 495354 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.2619. Min Act: -0.1700
Data Index: 7112106 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.2619. Min Act: -0.1700
Data Index: 6518964 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.2619. Min Act: -0.1700
Data Index: 2022201 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.2619. Min Act: -0.1700
Data Index: 2912347 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.2619. Min Act: -0.1700
Data Index: 3799241 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #19