Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3918 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.7253. Min Act: -0.1700
Data Index: 1852312 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.6316. Min Act: -0.1700
Data Index: 80918 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.6003. Min Act: -0.1700
Data Index: 6913289 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.5378. Min Act: -0.1700
Data Index: 7938585 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.5378. Min Act: -0.1700
Data Index: 1839961 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.5378. Min Act: -0.1700
Data Index: 7282114 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.5066. Min Act: -0.1700
Data Index: 6896946 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.4753. Min Act: -0.1700
Data Index: 6219347 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.4753. Min Act: -0.1700
Data Index: 3059873 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.4441. Min Act: -0.1700
Data Index: 1844226 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.4441. Min Act: -0.1700
Data Index: 8453697 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.4128. Min Act: -0.1700
Data Index: 6513228 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.3816. Min Act: -0.1700
Data Index: 4985751 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.3816. Min Act: -0.1700
Data Index: 962799 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.3816. Min Act: -0.1700
Data Index: 8546109 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.3816. Min Act: -0.1700
Data Index: 2640206 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.3816. Min Act: -0.1700
Data Index: 8713467 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.3816. Min Act: -0.1700
Data Index: 8716132 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.3503. Min Act: -0.1700
Data Index: 1368727 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.3503. Min Act: -0.1700
Data Index: 1067086 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #19