Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5309 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0177. Min Range: -5.0177
Max Act: 5.0177. Min Act: -0.1700
Data Index: 1069693 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0177. Min Range: -5.0177
Max Act: 4.8302. Min Act: -0.1700
Data Index: 5711842 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0177. Min Range: -5.0177
Max Act: 4.8302. Min Act: -0.1700
Data Index: 6294951 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0177. Min Range: -5.0177
Max Act: 4.7677. Min Act: -0.1700
Data Index: 4073081 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0177. Min Range: -5.0177
Max Act: 4.7989. Min Act: -0.1700
Data Index: 4466341 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0177. Min Range: -5.0177
Max Act: 4.7364. Min Act: -0.1700
Data Index: 3173526 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0177. Min Range: -5.0177
Max Act: 4.7052. Min Act: -0.1700
Data Index: 2650253 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0177. Min Range: -5.0177
Max Act: 4.7052. Min Act: -0.1700
Data Index: 3796274 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0177. Min Range: -5.0177
Max Act: 4.7052. Min Act: -0.1700
Data Index: 1481948 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0177. Min Range: -5.0177
Max Act: 4.6739. Min Act: -0.1700
Data Index: 2281227 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0177. Min Range: -5.0177
Max Act: 4.6739. Min Act: -0.1700
Data Index: 8298164 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0177. Min Range: -5.0177
Max Act: 4.6739. Min Act: -0.1700
Data Index: 6635830 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0177. Min Range: -5.0177
Max Act: 4.6739. Min Act: -0.1700
Data Index: 5351462 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0177. Min Range: -5.0177
Max Act: 4.6427. Min Act: -0.1700
Data Index: 7231125 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0177. Min Range: -5.0177
Max Act: 4.6427. Min Act: -0.1700
Data Index: 6956154 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0177. Min Range: -5.0177
Max Act: 4.6427. Min Act: -0.1700
Data Index: 750823 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0177. Min Range: -5.0177
Max Act: 4.6427. Min Act: -0.1700
Data Index: 3993931 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0177. Min Range: -5.0177
Max Act: 4.6114. Min Act: -0.1700
Data Index: 3258744 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0177. Min Range: -5.0177
Max Act: 4.6114. Min Act: -0.1700
Data Index: 1781708 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0177. Min Range: -5.0177
Max Act: 4.5802. Min Act: -0.1700
Data Index: 2812301 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19