Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2227 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7066. Min Range: -5.7066
Max Act: 5.7066. Min Act: -0.1700
Data Index: 452115 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7066. Min Range: -5.7066
Max Act: 5.6441. Min Act: -0.1700
Data Index: 3866636 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7066. Min Range: -5.7066
Max Act: 5.5816. Min Act: -0.1700
Data Index: 6475453 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7066. Min Range: -5.7066
Max Act: 5.5504. Min Act: -0.1700
Data Index: 5030468 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7066. Min Range: -5.7066
Max Act: 5.4879. Min Act: -0.1700
Data Index: 8156189 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7066. Min Range: -5.7066
Max Act: 5.4566. Min Act: -0.1700
Data Index: 3737281 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7066. Min Range: -5.7066
Max Act: 5.3941. Min Act: -0.1700
Data Index: 6475451 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7066. Min Range: -5.7066
Max Act: 5.3941. Min Act: -0.1700
Data Index: 1813628 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7066. Min Range: -5.7066
Max Act: 5.3941. Min Act: -0.1700
Data Index: 6212633 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7066. Min Range: -5.7066
Max Act: 5.3629. Min Act: -0.1700
Data Index: 2013700 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7066. Min Range: -5.7066
Max Act: 5.3629. Min Act: -0.1700
Data Index: 6193655 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7066. Min Range: -5.7066
Max Act: 5.3316. Min Act: -0.1700
Data Index: 5124400 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7066. Min Range: -5.7066
Max Act: 5.3316. Min Act: -0.1700
Data Index: 3082582 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7066. Min Range: -5.7066
Max Act: 5.3316. Min Act: -0.1700
Data Index: 76327 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7066. Min Range: -5.7066
Max Act: 5.3004. Min Act: -0.1700
Data Index: 6275017 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7066. Min Range: -5.7066
Max Act: 5.3004. Min Act: -0.1700
Data Index: 7827833 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7066. Min Range: -5.7066
Max Act: 5.3004. Min Act: -0.1700
Data Index: 1813629 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7066. Min Range: -5.7066
Max Act: 5.2691. Min Act: -0.1700
Data Index: 2538226 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7066. Min Range: -5.7066
Max Act: 5.2691. Min Act: -0.1700
Data Index: 3866634 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7066. Min Range: -5.7066
Max Act: 5.2691. Min Act: -0.1700
Data Index: 7905501 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19