Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3256 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9847. Min Range: -8.9847
Max Act: 8.9847. Min Act: -0.1700
Data Index: 6485139 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9847. Min Range: -8.9847
Max Act: 8.4847. Min Act: -0.1700
Data Index: 5892961 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9847. Min Range: -8.9847
Max Act: 8.3597. Min Act: -0.1700
Data Index: 2545827 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9847. Min Range: -8.9847
Max Act: 8.3597. Min Act: -0.1700
Data Index: 4697464 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9847. Min Range: -8.9847
Max Act: 8.1722. Min Act: -0.1700
Data Index: 763114 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9847. Min Range: -8.9847
Max Act: 8.1722. Min Act: -0.1700
Data Index: 4507734 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9847. Min Range: -8.9847
Max Act: 8.1097. Min Act: -0.1700
Data Index: 3000215 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9847. Min Range: -8.9847
Max Act: 8.1097. Min Act: -0.1700
Data Index: 7771929 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9847. Min Range: -8.9847
Max Act: 8.1097. Min Act: -0.1700
Data Index: 5263624 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9847. Min Range: -8.9847
Max Act: 8.1097. Min Act: -0.1700
Data Index: 3207253 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9847. Min Range: -8.9847
Max Act: 8.0472. Min Act: -0.1700
Data Index: 2347335 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9847. Min Range: -8.9847
Max Act: 8.0160. Min Act: -0.1700
Data Index: 3475140 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9847. Min Range: -8.9847
Max Act: 7.9847. Min Act: -0.1700
Data Index: 342312 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9847. Min Range: -8.9847
Max Act: 7.9535. Min Act: -0.1700
Data Index: 6321497 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9847. Min Range: -8.9847
Max Act: 7.9535. Min Act: -0.1700
Data Index: 18103 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9847. Min Range: -8.9847
Max Act: 7.9222. Min Act: -0.1700
Data Index: 3901492 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9847. Min Range: -8.9847
Max Act: 7.9222. Min Act: -0.1700
Data Index: 6685024 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9847. Min Range: -8.9847
Max Act: 7.9222. Min Act: -0.1700
Data Index: 1618145 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9847. Min Range: -8.9847
Max Act: 7.9222. Min Act: -0.1700
Data Index: 508762 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9847. Min Range: -8.9847
Max Act: 7.8910. Min Act: -0.1700
Data Index: 6379840 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19