Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3305 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7137. Min Range: -4.7137
Max Act: 4.7137. Min Act: -0.1700
Data Index: 2667625 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7137. Min Range: -4.7137
Max Act: 4.5887. Min Act: -0.1700
Data Index: 5427221 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7137. Min Range: -4.7137
Max Act: 4.5887. Min Act: -0.1700
Data Index: 3665114 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7137. Min Range: -4.7137
Max Act: 4.5262. Min Act: -0.1700
Data Index: 2514205 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7137. Min Range: -4.7137
Max Act: 4.4324. Min Act: -0.1700
Data Index: 8162195 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7137. Min Range: -4.7137
Max Act: 4.4324. Min Act: -0.1700
Data Index: 4546046 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7137. Min Range: -4.7137
Max Act: 4.4012. Min Act: -0.1700
Data Index: 1489892 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7137. Min Range: -4.7137
Max Act: 4.4012. Min Act: -0.1700
Data Index: 4492041 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7137. Min Range: -4.7137
Max Act: 4.4012. Min Act: -0.1700
Data Index: 3151167 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7137. Min Range: -4.7137
Max Act: 4.3699. Min Act: -0.1700
Data Index: 2556187 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7137. Min Range: -4.7137
Max Act: 4.3699. Min Act: -0.1700
Data Index: 8467338 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7137. Min Range: -4.7137
Max Act: 4.3387. Min Act: -0.1700
Data Index: 8300420 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7137. Min Range: -4.7137
Max Act: 4.3387. Min Act: -0.1700
Data Index: 8694842 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7137. Min Range: -4.7137
Max Act: 4.3387. Min Act: -0.1700
Data Index: 5551091 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7137. Min Range: -4.7137
Max Act: 4.3387. Min Act: -0.1700
Data Index: 4832626 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7137. Min Range: -4.7137
Max Act: 4.3074. Min Act: -0.1700
Data Index: 3303544 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7137. Min Range: -4.7137
Max Act: 4.3074. Min Act: -0.1700
Data Index: 3413745 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7137. Min Range: -4.7137
Max Act: 4.3074. Min Act: -0.1700
Data Index: 3470457 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7137. Min Range: -4.7137
Max Act: 4.2449. Min Act: -0.1700
Data Index: 5255040 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7137. Min Range: -4.7137
Max Act: 4.2762. Min Act: -0.1700
Data Index: 6422982 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19