Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3216 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.6600. Min Act: -0.1700
Data Index: 6816442 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.6600. Min Act: -0.1700
Data Index: 3677105 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.6287. Min Act: -0.1700
Data Index: 4416207 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.5661. Min Act: -0.1700
Data Index: 4049351 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.5817. Min Act: -0.1700
Data Index: 3211940 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.5504. Min Act: -0.1700
Data Index: 6898915 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.5504. Min Act: -0.1700
Data Index: 4395789 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.5504. Min Act: -0.1700
Data Index: 1853563 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.5191. Min Act: -0.1700
Data Index: 2065215 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.5504. Min Act: -0.1700
Data Index: 7297367 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.5034. Min Act: -0.1700
Data Index: 1089663 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.5348. Min Act: -0.1700
Data Index: 161103 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.5348. Min Act: -0.1700
Data Index: 1881250 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.5348. Min Act: -0.1700
Data Index: 5430688 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.5191. Min Act: -0.1700
Data Index: 7078957 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.5034. Min Act: -0.1700
Data Index: 8108613 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.5034. Min Act: -0.1700
Data Index: 8508635 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.4878. Min Act: -0.1700
Data Index: 2202262 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.4878. Min Act: -0.1700
Data Index: 6455909 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.4878. Min Act: -0.1700
Data Index: 8279774 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19