Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1058 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.4100. Min Act: -0.1700
Data Index: 5805847 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.3787. Min Act: -0.1700
Data Index: 3139679 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.2850. Min Act: -0.1700
Data Index: 7625640 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.2850. Min Act: -0.1700
Data Index: 2588309 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.3162. Min Act: -0.1700
Data Index: 6873311 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.3162. Min Act: -0.1700
Data Index: 5696271 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.2850. Min Act: -0.1700
Data Index: 3344602 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.2850. Min Act: -0.1700
Data Index: 4333285 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.2850. Min Act: -0.1700
Data Index: 4694222 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.2537. Min Act: -0.1700
Data Index: 2810796 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.2225. Min Act: -0.1700
Data Index: 1595884 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.2225. Min Act: -0.1700
Data Index: 7778543 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.1912. Min Act: -0.1700
Data Index: 6746416 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.1912. Min Act: -0.1700
Data Index: 7561905 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.1912. Min Act: -0.1700
Data Index: 4020337 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.1600. Min Act: -0.1700
Data Index: 495637 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.1912. Min Act: -0.1700
Data Index: 4763052 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.1912. Min Act: -0.1700
Data Index: 6076249 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.1912. Min Act: -0.1700
Data Index: 4227627 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.1912. Min Act: -0.1700
Data Index: 3038127 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19