Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3632 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0684. Min Range: -6.0684
Max Act: 6.0684. Min Act: -0.1700
Data Index: 5866720 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0684. Min Range: -6.0684
Max Act: 6.0059. Min Act: -0.1700
Data Index: 8108374 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0684. Min Range: -6.0684
Max Act: 5.7559. Min Act: -0.1700
Data Index: 1429135 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0684. Min Range: -6.0684
Max Act: 5.7559. Min Act: -0.1700
Data Index: 3601126 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0684. Min Range: -6.0684
Max Act: 5.6934. Min Act: -0.1700
Data Index: 61031 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0684. Min Range: -6.0684
Max Act: 5.6934. Min Act: -0.1700
Data Index: 6950067 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0684. Min Range: -6.0684
Max Act: 5.6934. Min Act: -0.1700
Data Index: 2405219 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0684. Min Range: -6.0684
Max Act: 5.6621. Min Act: -0.1700
Data Index: 4617123 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0684. Min Range: -6.0684
Max Act: 5.6621. Min Act: -0.1700
Data Index: 4099744 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0684. Min Range: -6.0684
Max Act: 5.6309. Min Act: -0.1700
Data Index: 2360385 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0684. Min Range: -6.0684
Max Act: 5.5684. Min Act: -0.1700
Data Index: 7569052 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0684. Min Range: -6.0684
Max Act: 5.5996. Min Act: -0.1700
Data Index: 857025 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0684. Min Range: -6.0684
Max Act: 5.5684. Min Act: -0.1700
Data Index: 995768 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0684. Min Range: -6.0684
Max Act: 5.5996. Min Act: -0.1700
Data Index: 7350959 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0684. Min Range: -6.0684
Max Act: 5.5684. Min Act: -0.1700
Data Index: 8255590 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0684. Min Range: -6.0684
Max Act: 5.5684. Min Act: -0.1700
Data Index: 145680 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0684. Min Range: -6.0684
Max Act: 5.5684. Min Act: -0.1700
Data Index: 5397425 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0684. Min Range: -6.0684
Max Act: 5.5684. Min Act: -0.1700
Data Index: 8665639 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0684. Min Range: -6.0684
Max Act: 5.5059. Min Act: -0.1700
Data Index: 5613727 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0684. Min Range: -6.0684
Max Act: 5.5059. Min Act: -0.1700
Data Index: 7712022 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19