Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3496 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5764. Min Range: -4.5764
Max Act: 4.5764. Min Act: -0.1700
Data Index: 3045515 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5764. Min Range: -4.5764
Max Act: 4.4827. Min Act: -0.1700
Data Index: 4358678 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5764. Min Range: -4.5764
Max Act: 4.4202. Min Act: -0.1700
Data Index: 1623422 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5764. Min Range: -4.5764
Max Act: 4.3577. Min Act: -0.1700
Data Index: 3597923 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5764. Min Range: -4.5764
Max Act: 4.3577. Min Act: -0.1700
Data Index: 8362836 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5764. Min Range: -4.5764
Max Act: 4.3577. Min Act: -0.1700
Data Index: 5288149 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5764. Min Range: -4.5764
Max Act: 4.3577. Min Act: -0.1700
Data Index: 4720537 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5764. Min Range: -4.5764
Max Act: 4.3264. Min Act: -0.1700
Data Index: 7814395 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5764. Min Range: -4.5764
Max Act: 4.2639. Min Act: -0.1700
Data Index: 274993 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5764. Min Range: -4.5764
Max Act: 4.2952. Min Act: -0.1700
Data Index: 5282013 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5764. Min Range: -4.5764
Max Act: 4.2639. Min Act: -0.1700
Data Index: 6446205 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5764. Min Range: -4.5764
Max Act: 4.2327. Min Act: -0.1700
Data Index: 4455735 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5764. Min Range: -4.5764
Max Act: 4.2639. Min Act: -0.1700
Data Index: 4941683 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5764. Min Range: -4.5764
Max Act: 4.2952. Min Act: -0.1700
Data Index: 6384671 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5764. Min Range: -4.5764
Max Act: 4.2639. Min Act: -0.1700
Data Index: 6455843 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5764. Min Range: -4.5764
Max Act: 4.2952. Min Act: -0.1700
Data Index: 2707189 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5764. Min Range: -4.5764
Max Act: 4.2639. Min Act: -0.1700
Data Index: 5773947 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5764. Min Range: -4.5764
Max Act: 4.2327. Min Act: -0.1700
Data Index: 7405112 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5764. Min Range: -4.5764
Max Act: 4.2327. Min Act: -0.1700
Data Index: 4720540 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5764. Min Range: -4.5764
Max Act: 4.2639. Min Act: -0.1700
Data Index: 191625 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #19