Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5681 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3748. Min Range: -5.3748
Max Act: 5.3748. Min Act: -0.1700
Data Index: 1962920 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3748. Min Range: -5.3748
Max Act: 5.3123. Min Act: -0.1700
Data Index: 448712 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3748. Min Range: -5.3748
Max Act: 5.2185. Min Act: -0.1700
Data Index: 3183158 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3748. Min Range: -5.3748
Max Act: 5.2185. Min Act: -0.1700
Data Index: 5106807 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3748. Min Range: -5.3748
Max Act: 5.1873. Min Act: -0.1700
Data Index: 7877590 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3748. Min Range: -5.3748
Max Act: 5.0935. Min Act: -0.1700
Data Index: 6908909 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3748. Min Range: -5.3748
Max Act: 5.0623. Min Act: -0.1700
Data Index: 5849987 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3748. Min Range: -5.3748
Max Act: 5.0623. Min Act: -0.1700
Data Index: 599652 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3748. Min Range: -5.3748
Max Act: 5.0310. Min Act: -0.1700
Data Index: 4069644 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3748. Min Range: -5.3748
Max Act: 4.9998. Min Act: -0.1700
Data Index: 6641781 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3748. Min Range: -5.3748
Max Act: 4.9998. Min Act: -0.1700
Data Index: 6057880 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3748. Min Range: -5.3748
Max Act: 4.9685. Min Act: -0.1700
Data Index: 3071703 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3748. Min Range: -5.3748
Max Act: 4.9060. Min Act: -0.1700
Data Index: 483291 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3748. Min Range: -5.3748
Max Act: 4.9060. Min Act: -0.1700
Data Index: 5958926 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3748. Min Range: -5.3748
Max Act: 4.8435. Min Act: -0.1700
Data Index: 7735474 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3748. Min Range: -5.3748
Max Act: 4.8435. Min Act: -0.1700
Data Index: 7182636 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3748. Min Range: -5.3748
Max Act: 4.8435. Min Act: -0.1700
Data Index: 3591540 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3748. Min Range: -5.3748
Max Act: 4.8435. Min Act: -0.1700
Data Index: 3801183 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3748. Min Range: -5.3748
Max Act: 4.8435. Min Act: -0.1700
Data Index: 1070632 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3748. Min Range: -5.3748
Max Act: 4.8435. Min Act: -0.1700
Data Index: 5505919 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19