Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2206 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6135. Min Range: -8.6135
Max Act: 8.6135. Min Act: -0.1700
Data Index: 6475563 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6135. Min Range: -8.6135
Max Act: 8.6135. Min Act: -0.1700
Data Index: 3190021 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6135. Min Range: -8.6135
Max Act: 8.4885. Min Act: -0.1700
Data Index: 5674244 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6135. Min Range: -8.6135
Max Act: 8.2385. Min Act: -0.1700
Data Index: 3527875 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6135. Min Range: -8.6135
Max Act: 8.2385. Min Act: -0.1700
Data Index: 5981456 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6135. Min Range: -8.6135
Max Act: 8.1760. Min Act: -0.1700
Data Index: 5500172 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6135. Min Range: -8.6135
Max Act: 8.0822. Min Act: -0.1700
Data Index: 2118108 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6135. Min Range: -8.6135
Max Act: 8.0510. Min Act: -0.1700
Data Index: 6793119 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6135. Min Range: -8.6135
Max Act: 8.0510. Min Act: -0.1700
Data Index: 1254887 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6135. Min Range: -8.6135
Max Act: 7.9885. Min Act: -0.1700
Data Index: 7722025 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6135. Min Range: -8.6135
Max Act: 8.0197. Min Act: -0.1700
Data Index: 7507523 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6135. Min Range: -8.6135
Max Act: 7.9885. Min Act: -0.1700
Data Index: 7658494 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6135. Min Range: -8.6135
Max Act: 7.9260. Min Act: -0.1700
Data Index: 7779455 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6135. Min Range: -8.6135
Max Act: 7.9260. Min Act: -0.1700
Data Index: 8044031 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6135. Min Range: -8.6135
Max Act: 7.8947. Min Act: -0.1700
Data Index: 2411839 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6135. Min Range: -8.6135
Max Act: 7.8947. Min Act: -0.1700
Data Index: 4620608 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6135. Min Range: -8.6135
Max Act: 7.8947. Min Act: -0.1700
Data Index: 1941837 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6135. Min Range: -8.6135
Max Act: 7.8635. Min Act: -0.1700
Data Index: 423753 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6135. Min Range: -8.6135
Max Act: 7.8322. Min Act: -0.1700
Data Index: 749962 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6135. Min Range: -8.6135
Max Act: 7.8010. Min Act: -0.1700
Data Index: 3993746 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19