Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3443 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2261. Min Range: -5.2261
Max Act: 5.2261. Min Act: -0.1700
Data Index: 4820115 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2261. Min Range: -5.2261
Max Act: 5.1949. Min Act: -0.1700
Data Index: 1194884 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2261. Min Range: -5.2261
Max Act: 5.1949. Min Act: -0.1700
Data Index: 646483 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2261. Min Range: -5.2261
Max Act: 5.1324. Min Act: -0.1700
Data Index: 1417318 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2261. Min Range: -5.2261
Max Act: 5.1011. Min Act: -0.1700
Data Index: 4794928 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2261. Min Range: -5.2261
Max Act: 5.0074. Min Act: -0.1700
Data Index: 2657666 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2261. Min Range: -5.2261
Max Act: 4.9761. Min Act: -0.1700
Data Index: 1672897 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2261. Min Range: -5.2261
Max Act: 4.9761. Min Act: -0.1700
Data Index: 7264983 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2261. Min Range: -5.2261
Max Act: 4.9449. Min Act: -0.1700
Data Index: 851415 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2261. Min Range: -5.2261
Max Act: 4.9136. Min Act: -0.1700
Data Index: 8385283 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2261. Min Range: -5.2261
Max Act: 4.9449. Min Act: -0.1700
Data Index: 4528238 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2261. Min Range: -5.2261
Max Act: 4.9449. Min Act: -0.1700
Data Index: 8302098 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2261. Min Range: -5.2261
Max Act: 4.9136. Min Act: -0.1700
Data Index: 8828871 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2261. Min Range: -5.2261
Max Act: 4.9136. Min Act: -0.1700
Data Index: 4813838 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2261. Min Range: -5.2261
Max Act: 4.8824. Min Act: -0.1700
Data Index: 7017351 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2261. Min Range: -5.2261
Max Act: 4.8824. Min Act: -0.1700
Data Index: 7948342 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2261. Min Range: -5.2261
Max Act: 4.8511. Min Act: -0.1700
Data Index: 2116293 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2261. Min Range: -5.2261
Max Act: 4.8511. Min Act: -0.1700
Data Index: 6871145 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2261. Min Range: -5.2261
Max Act: 4.8511. Min Act: -0.1700
Data Index: 4015120 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2261. Min Range: -5.2261
Max Act: 4.8511. Min Act: -0.1700
Data Index: 5731701 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19