Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3929 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8631. Min Range: -4.8631
Max Act: 4.8631. Min Act: -0.1700
Data Index: 4330478 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8631. Min Range: -4.8631
Max Act: 4.8319. Min Act: -0.1700
Data Index: 5091671 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8631. Min Range: -4.8631
Max Act: 4.7381. Min Act: -0.1700
Data Index: 5716358 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8631. Min Range: -4.8631
Max Act: 4.6444. Min Act: -0.1700
Data Index: 3731298 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8631. Min Range: -4.8631
Max Act: 4.6444. Min Act: -0.1700
Data Index: 8173732 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8631. Min Range: -4.8631
Max Act: 4.6131. Min Act: -0.1700
Data Index: 248840 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8631. Min Range: -4.8631
Max Act: 4.6444. Min Act: -0.1700
Data Index: 8249908 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8631. Min Range: -4.8631
Max Act: 4.6131. Min Act: -0.1700
Data Index: 4912664 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8631. Min Range: -4.8631
Max Act: 4.5819. Min Act: -0.1700
Data Index: 8232824 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8631. Min Range: -4.8631
Max Act: 4.5819. Min Act: -0.1700
Data Index: 4388293 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8631. Min Range: -4.8631
Max Act: 4.5819. Min Act: -0.1700
Data Index: 3948847 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8631. Min Range: -4.8631
Max Act: 4.5506. Min Act: -0.1700
Data Index: 7339151 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8631. Min Range: -4.8631
Max Act: 4.5819. Min Act: -0.1700
Data Index: 3641716 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8631. Min Range: -4.8631
Max Act: 4.5506. Min Act: -0.1700
Data Index: 7845957 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8631. Min Range: -4.8631
Max Act: 4.5506. Min Act: -0.1700
Data Index: 7317265 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8631. Min Range: -4.8631
Max Act: 4.5506. Min Act: -0.1700
Data Index: 6857081 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8631. Min Range: -4.8631
Max Act: 4.5193. Min Act: -0.1700
Data Index: 2677429 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8631. Min Range: -4.8631
Max Act: 4.5193. Min Act: -0.1700
Data Index: 7845959 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8631. Min Range: -4.8631
Max Act: 4.5193. Min Act: -0.1700
Data Index: 3382711 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8631. Min Range: -4.8631
Max Act: 4.4881. Min Act: -0.1700
Data Index: 1586725 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19