Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3448 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2714. Min Range: -5.2714
Max Act: 5.2714. Min Act: -0.1700
Data Index: 3852428 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2714. Min Range: -5.2714
Max Act: 4.9277. Min Act: -0.1700
Data Index: 8682354 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2714. Min Range: -5.2714
Max Act: 4.9277. Min Act: -0.1700
Data Index: 2693813 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2714. Min Range: -5.2714
Max Act: 4.9277. Min Act: -0.1700
Data Index: 7409666 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2714. Min Range: -5.2714
Max Act: 4.8652. Min Act: -0.1700
Data Index: 7685176 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2714. Min Range: -5.2714
Max Act: 4.8964. Min Act: -0.1700
Data Index: 8482874 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2714. Min Range: -5.2714
Max Act: 4.8339. Min Act: -0.1700
Data Index: 1967045 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2714. Min Range: -5.2714
Max Act: 4.7714. Min Act: -0.1700
Data Index: 598091 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2714. Min Range: -5.2714
Max Act: 4.7714. Min Act: -0.1700
Data Index: 6624067 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2714. Min Range: -5.2714
Max Act: 4.8027. Min Act: -0.1700
Data Index: 6231157 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2714. Min Range: -5.2714
Max Act: 4.7089. Min Act: -0.1700
Data Index: 5001276 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2714. Min Range: -5.2714
Max Act: 4.7402. Min Act: -0.1700
Data Index: 874656 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2714. Min Range: -5.2714
Max Act: 4.7089. Min Act: -0.1700
Data Index: 820606 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2714. Min Range: -5.2714
Max Act: 4.7089. Min Act: -0.1700
Data Index: 8567768 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2714. Min Range: -5.2714
Max Act: 4.6777. Min Act: -0.1700
Data Index: 4002691 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2714. Min Range: -5.2714
Max Act: 4.6777. Min Act: -0.1700
Data Index: 6164480 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2714. Min Range: -5.2714
Max Act: 4.6464. Min Act: -0.1700
Data Index: 5055144 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2714. Min Range: -5.2714
Max Act: 4.6464. Min Act: -0.1700
Data Index: 5598340 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2714. Min Range: -5.2714
Max Act: 4.6464. Min Act: -0.1700
Data Index: 1725693 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2714. Min Range: -5.2714
Max Act: 4.6464. Min Act: -0.1700
Data Index: 2241545 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19