Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 508 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2543. Min Range: -6.2543
Max Act: 6.2543. Min Act: -0.1700
Data Index: 7479627 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2543. Min Range: -6.2543
Max Act: 6.1293. Min Act: -0.1700
Data Index: 76765 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2543. Min Range: -6.2543
Max Act: 5.9105. Min Act: -0.1700
Data Index: 7785543 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2543. Min Range: -6.2543
Max Act: 5.9105. Min Act: -0.1700
Data Index: 1935483 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2543. Min Range: -6.2543
Max Act: 5.9105. Min Act: -0.1700
Data Index: 6218970 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2543. Min Range: -6.2543
Max Act: 5.8480. Min Act: -0.1700
Data Index: 6218968 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2543. Min Range: -6.2543
Max Act: 5.8793. Min Act: -0.1700
Data Index: 1977753 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2543. Min Range: -6.2543
Max Act: 5.8793. Min Act: -0.1700
Data Index: 3761915 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2543. Min Range: -6.2543
Max Act: 5.8168. Min Act: -0.1700
Data Index: 4215615 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2543. Min Range: -6.2543
Max Act: 5.8168. Min Act: -0.1700
Data Index: 2530116 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2543. Min Range: -6.2543
Max Act: 5.7855. Min Act: -0.1700
Data Index: 5599258 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2543. Min Range: -6.2543
Max Act: 5.7855. Min Act: -0.1700
Data Index: 1393048 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2543. Min Range: -6.2543
Max Act: 5.7543. Min Act: -0.1700
Data Index: 1464624 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2543. Min Range: -6.2543
Max Act: 5.7543. Min Act: -0.1700
Data Index: 3542847 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2543. Min Range: -6.2543
Max Act: 5.7230. Min Act: -0.1700
Data Index: 4254753 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2543. Min Range: -6.2543
Max Act: 5.7230. Min Act: -0.1700
Data Index: 7090471 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2543. Min Range: -6.2543
Max Act: 5.7230. Min Act: -0.1700
Data Index: 7450436 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2543. Min Range: -6.2543
Max Act: 5.7230. Min Act: -0.1700
Data Index: 7748709 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2543. Min Range: -6.2543
Max Act: 5.7230. Min Act: -0.1700
Data Index: 3963211 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2543. Min Range: -6.2543
Max Act: 5.7230. Min Act: -0.1700
Data Index: 1814779 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19