Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 541 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8214. Min Range: -4.8214
Max Act: 4.8214. Min Act: -0.1700
Data Index: 1593218 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8214. Min Range: -4.8214
Max Act: 4.7901. Min Act: -0.1700
Data Index: 8747999 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8214. Min Range: -4.8214
Max Act: 4.7589. Min Act: -0.1700
Data Index: 3169757 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8214. Min Range: -4.8214
Max Act: 4.7276. Min Act: -0.1700
Data Index: 4853194 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8214. Min Range: -4.8214
Max Act: 4.6651. Min Act: -0.1700
Data Index: 8544434 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8214. Min Range: -4.8214
Max Act: 4.6651. Min Act: -0.1700
Data Index: 4272968 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8214. Min Range: -4.8214
Max Act: 4.6964. Min Act: -0.1700
Data Index: 5589699 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8214. Min Range: -4.8214
Max Act: 4.6651. Min Act: -0.1700
Data Index: 1403103 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8214. Min Range: -4.8214
Max Act: 4.5714. Min Act: -0.1700
Data Index: 7580438 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8214. Min Range: -4.8214
Max Act: 4.6026. Min Act: -0.1700
Data Index: 4811490 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8214. Min Range: -4.8214
Max Act: 4.5714. Min Act: -0.1700
Data Index: 6126898 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8214. Min Range: -4.8214
Max Act: 4.5089. Min Act: -0.1700
Data Index: 3259631 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8214. Min Range: -4.8214
Max Act: 4.5401. Min Act: -0.1700
Data Index: 6906334 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8214. Min Range: -4.8214
Max Act: 4.5401. Min Act: -0.1700
Data Index: 6339450 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8214. Min Range: -4.8214
Max Act: 4.5089. Min Act: -0.1700
Data Index: 7444548 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8214. Min Range: -4.8214
Max Act: 4.4776. Min Act: -0.1700
Data Index: 4223258 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8214. Min Range: -4.8214
Max Act: 4.5089. Min Act: -0.1700
Data Index: 7396369 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8214. Min Range: -4.8214
Max Act: 4.5089. Min Act: -0.1700
Data Index: 6096608 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8214. Min Range: -4.8214
Max Act: 4.4464. Min Act: -0.1700
Data Index: 28066 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8214. Min Range: -4.8214
Max Act: 4.4776. Min Act: -0.1700
Data Index: 78455 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19