Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5825 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.3407. Min Act: -0.1700
Data Index: 4939510 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.3407. Min Act: -0.1700
Data Index: 653426 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.2782. Min Act: -0.1700
Data Index: 4947599 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.2470. Min Act: -0.1700
Data Index: 317707 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.2470. Min Act: -0.1700
Data Index: 503850 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.2470. Min Act: -0.1700
Data Index: 5082219 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.2157. Min Act: -0.1700
Data Index: 7014099 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.1532. Min Act: -0.1700
Data Index: 3840228 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.1532. Min Act: -0.1700
Data Index: 5358621 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.1532. Min Act: -0.1700
Data Index: 5754287 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.1845. Min Act: -0.1700
Data Index: 423137 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.1220. Min Act: -0.1700
Data Index: 1868824 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.1220. Min Act: -0.1700
Data Index: 6821013 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.1220. Min Act: -0.1700
Data Index: 246789 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.0907. Min Act: -0.1700
Data Index: 3132239 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.0907. Min Act: -0.1700
Data Index: 8684318 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.0907. Min Act: -0.1700
Data Index: 4384977 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.0594. Min Act: -0.1700
Data Index: 2477167 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.0594. Min Act: -0.1700
Data Index: 162832 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3407. Min Range: -4.3407
Max Act: 4.0594. Min Act: -0.1700
Data Index: 383461 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #19