Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2531 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7087. Min Range: -8.7087
Max Act: 8.7087. Min Act: -0.1700
Data Index: 7933032 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7087. Min Range: -8.7087
Max Act: 8.5212. Min Act: -0.1700
Data Index: 1479749 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7087. Min Range: -8.7087
Max Act: 8.3962. Min Act: -0.1700
Data Index: 287613 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7087. Min Range: -8.7087
Max Act: 8.1462. Min Act: -0.1700
Data Index: 41175 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7087. Min Range: -8.7087
Max Act: 8.0837. Min Act: -0.1700
Data Index: 4203906 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7087. Min Range: -8.7087
Max Act: 8.0837. Min Act: -0.1700
Data Index: 5039340 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7087. Min Range: -8.7087
Max Act: 7.9587. Min Act: -0.1700
Data Index: 7923030 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7087. Min Range: -8.7087
Max Act: 7.9587. Min Act: -0.1700
Data Index: 8012457 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7087. Min Range: -8.7087
Max Act: 7.9587. Min Act: -0.1700
Data Index: 714412 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7087. Min Range: -8.7087
Max Act: 7.8337. Min Act: -0.1700
Data Index: 3413718 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7087. Min Range: -8.7087
Max Act: 7.8962. Min Act: -0.1700
Data Index: 4104363 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7087. Min Range: -8.7087
Max Act: 7.8337. Min Act: -0.1700
Data Index: 4368460 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7087. Min Range: -8.7087
Max Act: 7.8337. Min Act: -0.1700
Data Index: 5018488 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7087. Min Range: -8.7087
Max Act: 7.8337. Min Act: -0.1700
Data Index: 8322360 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7087. Min Range: -8.7087
Max Act: 7.6462. Min Act: -0.1700
Data Index: 2376947 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7087. Min Range: -8.7087
Max Act: 7.6462. Min Act: -0.1700
Data Index: 3269327 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7087. Min Range: -8.7087
Max Act: 7.6462. Min Act: -0.1700
Data Index: 2321012 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7087. Min Range: -8.7087
Max Act: 7.6462. Min Act: -0.1700
Data Index: 5539283 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7087. Min Range: -8.7087
Max Act: 7.5837. Min Act: -0.1700
Data Index: 7616920 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7087. Min Range: -8.7087
Max Act: 7.5837. Min Act: -0.1700
Data Index: 1622245 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19