Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5446 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4639. Min Range: -3.4639
Max Act: 3.4639. Min Act: -0.1700
Data Index: 7737484 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4639. Min Range: -3.4639
Max Act: 3.3698. Min Act: -0.1700
Data Index: 3582321 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4639. Min Range: -3.4639
Max Act: 3.3541. Min Act: -0.1700
Data Index: 4658998 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4639. Min Range: -3.4639
Max Act: 3.3541. Min Act: -0.1700
Data Index: 8520122 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4639. Min Range: -3.4639
Max Act: 3.2914. Min Act: -0.1700
Data Index: 1503448 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4639. Min Range: -3.4639
Max Act: 3.2914. Min Act: -0.1700
Data Index: 5309851 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4639. Min Range: -3.4639
Max Act: 3.2600. Min Act: -0.1700
Data Index: 3610200 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4639. Min Range: -3.4639
Max Act: 3.2600. Min Act: -0.1700
Data Index: 6892411 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4639. Min Range: -3.4639
Max Act: 3.2128. Min Act: -0.1700
Data Index: 6968239 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4639. Min Range: -3.4639
Max Act: 3.2128. Min Act: -0.1700
Data Index: 2030399 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4639. Min Range: -3.4639
Max Act: 3.1814. Min Act: -0.1700
Data Index: 5130374 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4639. Min Range: -3.4639
Max Act: 3.1814. Min Act: -0.1700
Data Index: 7752580 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4639. Min Range: -3.4639
Max Act: 3.1656. Min Act: -0.1700
Data Index: 2740955 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4639. Min Range: -3.4639
Max Act: 3.1656. Min Act: -0.1700
Data Index: 1601598 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4639. Min Range: -3.4639
Max Act: 3.1499. Min Act: -0.1700
Data Index: 8779637 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4639. Min Range: -3.4639
Max Act: 3.1499. Min Act: -0.1700
Data Index: 7171821 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4639. Min Range: -3.4639
Max Act: 3.1341. Min Act: -0.1700
Data Index: 1430314 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4639. Min Range: -3.4639
Max Act: 3.1341. Min Act: -0.1700
Data Index: 1196954 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4639. Min Range: -3.4639
Max Act: 3.1184. Min Act: -0.1700
Data Index: 7943484 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4639. Min Range: -3.4639
Max Act: 3.1341. Min Act: -0.1696
Data Index: 5713553 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19