Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 874 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0645. Min Range: -8.0645
Max Act: 8.0645. Min Act: -0.1700
Data Index: 5907916 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0645. Min Range: -8.0645
Max Act: 6.9083. Min Act: -0.1700
Data Index: 4340412 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0645. Min Range: -8.0645
Max Act: 6.5333. Min Act: -0.1700
Data Index: 6646466 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0645. Min Range: -8.0645
Max Act: 6.3145. Min Act: -0.1700
Data Index: 6195748 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0645. Min Range: -8.0645
Max Act: 6.1895. Min Act: -0.1700
Data Index: 4779088 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0645. Min Range: -8.0645
Max Act: 5.2208. Min Act: -0.1700
Data Index: 6779693 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0645. Min Range: -8.0645
Max Act: 6.1895. Min Act: -0.1700
Data Index: 5652019 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0645. Min Range: -8.0645
Max Act: 5.9395. Min Act: -0.1700
Data Index: 135784 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0645. Min Range: -8.0645
Max Act: 5.4083. Min Act: -0.1700
Data Index: 8649785 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0645. Min Range: -8.0645
Max Act: 6.0645. Min Act: -0.1700
Data Index: 217111 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0645. Min Range: -8.0645
Max Act: 6.0333. Min Act: -0.1700
Data Index: 5521794 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0645. Min Range: -8.0645
Max Act: 5.7208. Min Act: -0.1700
Data Index: 6771012 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0645. Min Range: -8.0645
Max Act: 6.0645. Min Act: -0.1700
Data Index: 6773922 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0645. Min Range: -8.0645
Max Act: 6.0020. Min Act: -0.1700
Data Index: 5845052 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0645. Min Range: -8.0645
Max Act: 6.0020. Min Act: -0.1700
Data Index: 5567392 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0645. Min Range: -8.0645
Max Act: 6.0020. Min Act: -0.1700
Data Index: 2123046 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0645. Min Range: -8.0645
Max Act: 5.9395. Min Act: -0.1700
Data Index: 1811357 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0645. Min Range: -8.0645
Max Act: 5.9395. Min Act: -0.1700
Data Index: 63509 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0645. Min Range: -8.0645
Max Act: 5.9083. Min Act: -0.1700
Data Index: 7736412 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0645. Min Range: -8.0645
Max Act: 5.9395. Min Act: -0.1700
Data Index: 6687334 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19