Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3787 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4950. Min Range: -6.4950
Max Act: 6.4950. Min Act: -0.1700
Data Index: 7562515 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4950. Min Range: -6.4950
Max Act: 6.3700. Min Act: -0.1700
Data Index: 7388 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4950. Min Range: -6.4950
Max Act: 6.3387. Min Act: -0.1700
Data Index: 5223243 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4950. Min Range: -6.4950
Max Act: 6.2762. Min Act: -0.1700
Data Index: 2037156 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4950. Min Range: -6.4950
Max Act: 6.2450. Min Act: -0.1700
Data Index: 2012090 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4950. Min Range: -6.4950
Max Act: 6.2450. Min Act: -0.1700
Data Index: 2374805 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4950. Min Range: -6.4950
Max Act: 6.2137. Min Act: -0.1700
Data Index: 1309326 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4950. Min Range: -6.4950
Max Act: 6.1200. Min Act: -0.1700
Data Index: 2392951 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4950. Min Range: -6.4950
Max Act: 6.0887. Min Act: -0.1700
Data Index: 5070416 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4950. Min Range: -6.4950
Max Act: 6.0575. Min Act: -0.1700
Data Index: 1387761 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4950. Min Range: -6.4950
Max Act: 6.0262. Min Act: -0.1700
Data Index: 708525 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4950. Min Range: -6.4950
Max Act: 5.9637. Min Act: -0.1700
Data Index: 8477357 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4950. Min Range: -6.4950
Max Act: 5.9325. Min Act: -0.1700
Data Index: 5039217 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4950. Min Range: -6.4950
Max Act: 5.9012. Min Act: -0.1700
Data Index: 3832429 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4950. Min Range: -6.4950
Max Act: 5.9012. Min Act: -0.1700
Data Index: 3742512 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4950. Min Range: -6.4950
Max Act: 5.9012. Min Act: -0.1700
Data Index: 5232577 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4950. Min Range: -6.4950
Max Act: 5.9012. Min Act: -0.1700
Data Index: 868221 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4950. Min Range: -6.4950
Max Act: 5.8387. Min Act: -0.1700
Data Index: 3070734 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4950. Min Range: -6.4950
Max Act: 5.8075. Min Act: -0.1700
Data Index: 6743318 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4950. Min Range: -6.4950
Max Act: 5.7762. Min Act: -0.1700
Data Index: 8458056 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19