Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2647 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1470. Min Range: -6.1470
Max Act: 6.1470. Min Act: -0.1700
Data Index: 4741195 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1470. Min Range: -6.1470
Max Act: 5.8345. Min Act: -0.1700
Data Index: 833114 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1470. Min Range: -6.1470
Max Act: 5.6782. Min Act: -0.1700
Data Index: 7019643 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1470. Min Range: -6.1470
Max Act: 5.5532. Min Act: -0.1700
Data Index: 1229467 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1470. Min Range: -6.1470
Max Act: 5.5532. Min Act: -0.1700
Data Index: 6794308 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1470. Min Range: -6.1470
Max Act: 5.5220. Min Act: -0.1700
Data Index: 7317806 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1470. Min Range: -6.1470
Max Act: 5.5220. Min Act: -0.1700
Data Index: 5338963 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1470. Min Range: -6.1470
Max Act: 5.5220. Min Act: -0.1700
Data Index: 3825784 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1470. Min Range: -6.1470
Max Act: 5.4907. Min Act: -0.1700
Data Index: 3576860 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1470. Min Range: -6.1470
Max Act: 5.4907. Min Act: -0.1700
Data Index: 4047917 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1470. Min Range: -6.1470
Max Act: 5.4907. Min Act: -0.1700
Data Index: 5287916 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1470. Min Range: -6.1470
Max Act: 5.4907. Min Act: -0.1700
Data Index: 2008058 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1470. Min Range: -6.1470
Max Act: 5.4595. Min Act: -0.1700
Data Index: 8454966 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1470. Min Range: -6.1470
Max Act: 5.4595. Min Act: -0.1700
Data Index: 172285 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1470. Min Range: -6.1470
Max Act: 5.4595. Min Act: -0.1700
Data Index: 6955135 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1470. Min Range: -6.1470
Max Act: 5.4595. Min Act: -0.1700
Data Index: 3632328 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1470. Min Range: -6.1470
Max Act: 5.4595. Min Act: -0.1700
Data Index: 3138079 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1470. Min Range: -6.1470
Max Act: 5.4595. Min Act: -0.1700
Data Index: 7393326 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1470. Min Range: -6.1470
Max Act: 5.4595. Min Act: -0.1700
Data Index: 6597994 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1470. Min Range: -6.1470
Max Act: 5.4282. Min Act: -0.1700
Data Index: 3530566 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #19