Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1820 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9086. Min Range: -4.9086
Max Act: 4.9086. Min Act: -0.1700
Data Index: 8018266 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9086. Min Range: -4.9086
Max Act: 4.8774. Min Act: -0.1700
Data Index: 5397670 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9086. Min Range: -4.9086
Max Act: 4.8149. Min Act: -0.1700
Data Index: 7516345 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9086. Min Range: -4.9086
Max Act: 4.7836. Min Act: -0.1700
Data Index: 5568766 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9086. Min Range: -4.9086
Max Act: 4.6899. Min Act: -0.1700
Data Index: 6074535 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9086. Min Range: -4.9086
Max Act: 4.6586. Min Act: -0.1700
Data Index: 3226367 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9086. Min Range: -4.9086
Max Act: 4.6899. Min Act: -0.1700
Data Index: 4904849 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9086. Min Range: -4.9086
Max Act: 4.7211. Min Act: -0.1700
Data Index: 8816048 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9086. Min Range: -4.9086
Max Act: 4.6899. Min Act: -0.1700
Data Index: 3798603 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9086. Min Range: -4.9086
Max Act: 4.6274. Min Act: -0.1700
Data Index: 4829188 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9086. Min Range: -4.9086
Max Act: 4.6899. Min Act: -0.1700
Data Index: 591559 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9086. Min Range: -4.9086
Max Act: 4.6274. Min Act: -0.1700
Data Index: 4524416 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9086. Min Range: -4.9086
Max Act: 4.6586. Min Act: -0.1700
Data Index: 797230 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9086. Min Range: -4.9086
Max Act: 4.5961. Min Act: -0.1700
Data Index: 144864 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9086. Min Range: -4.9086
Max Act: 4.6274. Min Act: -0.1700
Data Index: 144870 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9086. Min Range: -4.9086
Max Act: 4.6274. Min Act: -0.1700
Data Index: 1037981 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9086. Min Range: -4.9086
Max Act: 4.5649. Min Act: -0.1700
Data Index: 1780492 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9086. Min Range: -4.9086
Max Act: 4.5961. Min Act: -0.1700
Data Index: 2985386 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9086. Min Range: -4.9086
Max Act: 4.5649. Min Act: -0.1700
Data Index: 4899234 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9086. Min Range: -4.9086
Max Act: 4.5649. Min Act: -0.1700
Data Index: 2250040 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19