Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 791 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7702. Min Range: -6.7702
Max Act: 6.7702. Min Act: -0.1700
Data Index: 1653697 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7702. Min Range: -6.7702
Max Act: 6.6765. Min Act: -0.1700
Data Index: 1680439 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7702. Min Range: -6.7702
Max Act: 6.5515. Min Act: -0.1700
Data Index: 8301095 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7702. Min Range: -6.7702
Max Act: 6.4577. Min Act: -0.1700
Data Index: 5693907 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7702. Min Range: -6.7702
Max Act: 6.3640. Min Act: -0.1700
Data Index: 4912611 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7702. Min Range: -6.7702
Max Act: 6.3327. Min Act: -0.1700
Data Index: 7646383 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7702. Min Range: -6.7702
Max Act: 6.3640. Min Act: -0.1700
Data Index: 4010604 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7702. Min Range: -6.7702
Max Act: 6.3640. Min Act: -0.1700
Data Index: 2549751 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7702. Min Range: -6.7702
Max Act: 6.3640. Min Act: -0.1700
Data Index: 1553914 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7702. Min Range: -6.7702
Max Act: 6.3327. Min Act: -0.1700
Data Index: 3329010 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7702. Min Range: -6.7702
Max Act: 6.3640. Min Act: -0.1700
Data Index: 2029485 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7702. Min Range: -6.7702
Max Act: 6.3327. Min Act: -0.1700
Data Index: 2529597 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7702. Min Range: -6.7702
Max Act: 6.3015. Min Act: -0.1700
Data Index: 2025426 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7702. Min Range: -6.7702
Max Act: 6.2702. Min Act: -0.1700
Data Index: 6873218 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7702. Min Range: -6.7702
Max Act: 6.2390. Min Act: -0.1700
Data Index: 6668209 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7702. Min Range: -6.7702
Max Act: 6.2702. Min Act: -0.1700
Data Index: 526933 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7702. Min Range: -6.7702
Max Act: 6.2390. Min Act: -0.1700
Data Index: 6191930 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7702. Min Range: -6.7702
Max Act: 6.2702. Min Act: -0.1700
Data Index: 8627981 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7702. Min Range: -6.7702
Max Act: 6.2702. Min Act: -0.1700
Data Index: 309767 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7702. Min Range: -6.7702
Max Act: 6.2390. Min Act: -0.1700
Data Index: 3585475 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19