Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6104 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8908. Min Range: -7.8908
Max Act: 7.8908. Min Act: -0.1700
Data Index: 8569823 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8908. Min Range: -7.8908
Max Act: 7.4220. Min Act: -0.1700
Data Index: 4888756 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8908. Min Range: -7.8908
Max Act: 7.2970. Min Act: -0.1700
Data Index: 4901816 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8908. Min Range: -7.8908
Max Act: 7.2658. Min Act: -0.1700
Data Index: 1302584 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8908. Min Range: -7.8908
Max Act: 7.2658. Min Act: -0.1700
Data Index: 5635073 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8908. Min Range: -7.8908
Max Act: 7.2658. Min Act: -0.1700
Data Index: 3022862 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8908. Min Range: -7.8908
Max Act: 7.2345. Min Act: -0.1700
Data Index: 6041625 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8908. Min Range: -7.8908
Max Act: 7.2033. Min Act: -0.1700
Data Index: 8551745 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8908. Min Range: -7.8908
Max Act: 7.2033. Min Act: -0.1700
Data Index: 5483305 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8908. Min Range: -7.8908
Max Act: 7.1408. Min Act: -0.1700
Data Index: 5213612 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8908. Min Range: -7.8908
Max Act: 7.1095. Min Act: -0.1700
Data Index: 4509695 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8908. Min Range: -7.8908
Max Act: 7.1095. Min Act: -0.1700
Data Index: 126463 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8908. Min Range: -7.8908
Max Act: 7.1095. Min Act: -0.1700
Data Index: 6235116 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8908. Min Range: -7.8908
Max Act: 7.1095. Min Act: -0.1700
Data Index: 2301986 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8908. Min Range: -7.8908
Max Act: 7.0783. Min Act: -0.1700
Data Index: 5143860 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8908. Min Range: -7.8908
Max Act: 7.0783. Min Act: -0.1700
Data Index: 5599185 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8908. Min Range: -7.8908
Max Act: 7.0783. Min Act: -0.1700
Data Index: 4707203 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8908. Min Range: -7.8908
Max Act: 7.0470. Min Act: -0.1700
Data Index: 5697897 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8908. Min Range: -7.8908
Max Act: 7.0470. Min Act: -0.1700
Data Index: 4922734 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8908. Min Range: -7.8908
Max Act: 7.0470. Min Act: -0.1700
Data Index: 8394517 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19