Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4331 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4167. Min Range: -8.4167
Max Act: 8.4167. Min Act: -0.1700
Data Index: 5753185 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4167. Min Range: -8.4167
Max Act: 8.3542. Min Act: -0.1700
Data Index: 3359918 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4167. Min Range: -8.4167
Max Act: 8.2917. Min Act: -0.1700
Data Index: 2635583 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4167. Min Range: -8.4167
Max Act: 8.0417. Min Act: -0.1700
Data Index: 7178369 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4167. Min Range: -8.4167
Max Act: 7.9167. Min Act: -0.1700
Data Index: 615287 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4167. Min Range: -8.4167
Max Act: 7.9167. Min Act: -0.1700
Data Index: 6503324 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4167. Min Range: -8.4167
Max Act: 7.8542. Min Act: -0.1700
Data Index: 7014562 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4167. Min Range: -8.4167
Max Act: 7.8542. Min Act: -0.1700
Data Index: 3774311 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4167. Min Range: -8.4167
Max Act: 7.8542. Min Act: -0.1700
Data Index: 4118325 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4167. Min Range: -8.4167
Max Act: 7.7917. Min Act: -0.1700
Data Index: 7430300 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4167. Min Range: -8.4167
Max Act: 7.7292. Min Act: -0.1700
Data Index: 353823 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4167. Min Range: -8.4167
Max Act: 7.7292. Min Act: -0.1700
Data Index: 6160073 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4167. Min Range: -8.4167
Max Act: 7.6042. Min Act: -0.1700
Data Index: 6699131 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4167. Min Range: -8.4167
Max Act: 7.6667. Min Act: -0.1700
Data Index: 6546284 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4167. Min Range: -8.4167
Max Act: 7.6667. Min Act: -0.1700
Data Index: 5696475 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4167. Min Range: -8.4167
Max Act: 7.6042. Min Act: -0.1700
Data Index: 3711262 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4167. Min Range: -8.4167
Max Act: 7.5417. Min Act: -0.1700
Data Index: 2863531 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4167. Min Range: -8.4167
Max Act: 7.5417. Min Act: -0.1700
Data Index: 5638411 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4167. Min Range: -8.4167
Max Act: 7.5417. Min Act: -0.1700
Data Index: 1220028 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4167. Min Range: -8.4167
Max Act: 7.4792. Min Act: -0.1700
Data Index: 1980387 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19