Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2843 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9365. Min Range: -5.9365
Max Act: 5.9365. Min Act: -0.1700
Data Index: 3745047 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9365. Min Range: -5.9365
Max Act: 5.9365. Min Act: -0.1700
Data Index: 8397672 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9365. Min Range: -5.9365
Max Act: 5.9365. Min Act: -0.1700
Data Index: 2343222 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9365. Min Range: -5.9365
Max Act: 5.8428. Min Act: -0.1700
Data Index: 4267281 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9365. Min Range: -5.9365
Max Act: 5.8428. Min Act: -0.1700
Data Index: 842369 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9365. Min Range: -5.9365
Max Act: 5.8428. Min Act: -0.1700
Data Index: 7395082 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9365. Min Range: -5.9365
Max Act: 5.7803. Min Act: -0.1700
Data Index: 679073 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9365. Min Range: -5.9365
Max Act: 5.7803. Min Act: -0.1700
Data Index: 2838026 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9365. Min Range: -5.9365
Max Act: 5.7803. Min Act: -0.1700
Data Index: 4567364 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9365. Min Range: -5.9365
Max Act: 5.7490. Min Act: -0.1700
Data Index: 8793770 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9365. Min Range: -5.9365
Max Act: 5.7490. Min Act: -0.1700
Data Index: 5835019 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9365. Min Range: -5.9365
Max Act: 5.7178. Min Act: -0.1700
Data Index: 2188593 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9365. Min Range: -5.9365
Max Act: 5.6865. Min Act: -0.1700
Data Index: 8367330 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9365. Min Range: -5.9365
Max Act: 5.6240. Min Act: -0.1700
Data Index: 724901 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9365. Min Range: -5.9365
Max Act: 5.6240. Min Act: -0.1700
Data Index: 3203742 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9365. Min Range: -5.9365
Max Act: 5.6240. Min Act: -0.1700
Data Index: 6711003 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9365. Min Range: -5.9365
Max Act: 5.6240. Min Act: -0.1700
Data Index: 4790941 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9365. Min Range: -5.9365
Max Act: 5.6240. Min Act: -0.1700
Data Index: 5086759 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9365. Min Range: -5.9365
Max Act: 5.6240. Min Act: -0.1700
Data Index: 83229 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9365. Min Range: -5.9365
Max Act: 5.5928. Min Act: -0.1700
Data Index: 3053051 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19