Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 584 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8538. Min Range: -5.8538
Max Act: 5.8538. Min Act: -0.1700
Data Index: 245796 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8538. Min Range: -5.8538
Max Act: 5.8226. Min Act: -0.1700
Data Index: 4824859 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8538. Min Range: -5.8538
Max Act: 5.7601. Min Act: -0.1700
Data Index: 816587 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8538. Min Range: -5.8538
Max Act: 5.7288. Min Act: -0.1700
Data Index: 4339521 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8538. Min Range: -5.8538
Max Act: 5.6663. Min Act: -0.1700
Data Index: 3066122 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8538. Min Range: -5.8538
Max Act: 5.6663. Min Act: -0.1700
Data Index: 8493742 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8538. Min Range: -5.8538
Max Act: 5.6663. Min Act: -0.1700
Data Index: 5712220 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8538. Min Range: -5.8538
Max Act: 5.5726. Min Act: -0.1700
Data Index: 979114 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8538. Min Range: -5.8538
Max Act: 5.5726. Min Act: -0.1700
Data Index: 1129822 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8538. Min Range: -5.8538
Max Act: 5.5413. Min Act: -0.1700
Data Index: 694478 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8538. Min Range: -5.8538
Max Act: 5.5413. Min Act: -0.1700
Data Index: 6799256 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8538. Min Range: -5.8538
Max Act: 5.5413. Min Act: -0.1700
Data Index: 6494961 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8538. Min Range: -5.8538
Max Act: 5.5101. Min Act: -0.1700
Data Index: 4391960 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8538. Min Range: -5.8538
Max Act: 5.4476. Min Act: -0.1700
Data Index: 8246985 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8538. Min Range: -5.8538
Max Act: 5.4476. Min Act: -0.1700
Data Index: 442582 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8538. Min Range: -5.8538
Max Act: 5.4163. Min Act: -0.1700
Data Index: 5038485 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8538. Min Range: -5.8538
Max Act: 5.3851. Min Act: -0.1700
Data Index: 6685183 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8538. Min Range: -5.8538
Max Act: 5.3851. Min Act: -0.1700
Data Index: 7873457 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8538. Min Range: -5.8538
Max Act: 5.3538. Min Act: -0.1700
Data Index: 3609783 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8538. Min Range: -5.8538
Max Act: 5.3851. Min Act: -0.1700
Data Index: 5770083 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #19