Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4282 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7711. Min Range: -7.7711
Max Act: 7.7711. Min Act: -0.1700
Data Index: 3135423 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7711. Min Range: -7.7711
Max Act: 7.7711. Min Act: -0.1700
Data Index: 5020777 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7711. Min Range: -7.7711
Max Act: 7.6461. Min Act: -0.1700
Data Index: 862814 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7711. Min Range: -7.7711
Max Act: 7.6773. Min Act: -0.1700
Data Index: 2781007 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7711. Min Range: -7.7711
Max Act: 7.6461. Min Act: -0.1700
Data Index: 2283420 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7711. Min Range: -7.7711
Max Act: 7.6148. Min Act: -0.1700
Data Index: 2585376 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7711. Min Range: -7.7711
Max Act: 7.5836. Min Act: -0.1700
Data Index: 1080141 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7711. Min Range: -7.7711
Max Act: 7.5836. Min Act: -0.1700
Data Index: 8405110 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7711. Min Range: -7.7711
Max Act: 7.5211. Min Act: -0.1700
Data Index: 6015755 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7711. Min Range: -7.7711
Max Act: 7.4898. Min Act: -0.1700
Data Index: 2638549 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7711. Min Range: -7.7711
Max Act: 7.4898. Min Act: -0.1700
Data Index: 8169637 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7711. Min Range: -7.7711
Max Act: 7.4586. Min Act: -0.1700
Data Index: 1817772 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7711. Min Range: -7.7711
Max Act: 7.4586. Min Act: -0.1700
Data Index: 8134339 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7711. Min Range: -7.7711
Max Act: 7.4586. Min Act: -0.1700
Data Index: 1082807 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7711. Min Range: -7.7711
Max Act: 7.4586. Min Act: -0.1700
Data Index: 5518007 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7711. Min Range: -7.7711
Max Act: 7.3961. Min Act: -0.1700
Data Index: 4950087 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7711. Min Range: -7.7711
Max Act: 7.3961. Min Act: -0.1700
Data Index: 6297133 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7711. Min Range: -7.7711
Max Act: 7.3961. Min Act: -0.1700
Data Index: 8102844 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7711. Min Range: -7.7711
Max Act: 7.3336. Min Act: -0.1700
Data Index: 4922701 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7711. Min Range: -7.7711
Max Act: 7.3336. Min Act: -0.1700
Data Index: 5286279 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #19