Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3627 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5119. Min Range: -4.5119
Max Act: 4.5119. Min Act: -0.1700
Data Index: 5107528 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5119. Min Range: -4.5119
Max Act: 4.4494. Min Act: -0.1700
Data Index: 1291881 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5119. Min Range: -4.5119
Max Act: 4.3557. Min Act: -0.1700
Data Index: 6173092 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5119. Min Range: -4.5119
Max Act: 4.3557. Min Act: -0.1700
Data Index: 4321257 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5119. Min Range: -4.5119
Max Act: 4.3557. Min Act: -0.1700
Data Index: 4342758 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5119. Min Range: -4.5119
Max Act: 4.2932. Min Act: -0.1700
Data Index: 2571168 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5119. Min Range: -4.5119
Max Act: 4.2619. Min Act: -0.1700
Data Index: 7290858 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5119. Min Range: -4.5119
Max Act: 4.2619. Min Act: -0.1700
Data Index: 7324186 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5119. Min Range: -4.5119
Max Act: 4.2619. Min Act: -0.1700
Data Index: 197941 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5119. Min Range: -4.5119
Max Act: 4.2932. Min Act: -0.1700
Data Index: 4403285 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5119. Min Range: -4.5119
Max Act: 4.2307. Min Act: -0.1700
Data Index: 2858908 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5119. Min Range: -4.5119
Max Act: 4.2307. Min Act: -0.1700
Data Index: 5775028 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5119. Min Range: -4.5119
Max Act: 4.2307. Min Act: -0.1700
Data Index: 7548753 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5119. Min Range: -4.5119
Max Act: 4.1994. Min Act: -0.1700
Data Index: 7957831 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5119. Min Range: -4.5119
Max Act: 4.1994. Min Act: -0.1700
Data Index: 3509477 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5119. Min Range: -4.5119
Max Act: 4.1994. Min Act: -0.1700
Data Index: 1561877 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5119. Min Range: -4.5119
Max Act: 4.2307. Min Act: -0.1700
Data Index: 5125994 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5119. Min Range: -4.5119
Max Act: 4.1994. Min Act: -0.1700
Data Index: 3523311 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5119. Min Range: -4.5119
Max Act: 4.1994. Min Act: -0.1700
Data Index: 548961 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5119. Min Range: -4.5119
Max Act: 4.1682. Min Act: -0.1700
Data Index: 4438440 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #19