Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2444 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1364. Min Range: -6.1364
Max Act: 6.1364. Min Act: -0.1700
Data Index: 6004177 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1364. Min Range: -6.1364
Max Act: 6.0427. Min Act: -0.1700
Data Index: 8446818 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1364. Min Range: -6.1364
Max Act: 5.9489. Min Act: -0.1700
Data Index: 2563220 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1364. Min Range: -6.1364
Max Act: 5.9177. Min Act: -0.1700
Data Index: 5653575 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1364. Min Range: -6.1364
Max Act: 5.8864. Min Act: -0.1700
Data Index: 2386786 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1364. Min Range: -6.1364
Max Act: 5.8552. Min Act: -0.1700
Data Index: 1245076 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1364. Min Range: -6.1364
Max Act: 5.8552. Min Act: -0.1700
Data Index: 1862634 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1364. Min Range: -6.1364
Max Act: 5.7927. Min Act: -0.1700
Data Index: 1699771 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1364. Min Range: -6.1364
Max Act: 5.7614. Min Act: -0.1700
Data Index: 4386000 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1364. Min Range: -6.1364
Max Act: 5.7614. Min Act: -0.1700
Data Index: 4881381 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1364. Min Range: -6.1364
Max Act: 5.7614. Min Act: -0.1700
Data Index: 6605722 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1364. Min Range: -6.1364
Max Act: 5.7614. Min Act: -0.1700
Data Index: 7713463 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1364. Min Range: -6.1364
Max Act: 5.7302. Min Act: -0.1700
Data Index: 4678710 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1364. Min Range: -6.1364
Max Act: 5.6989. Min Act: -0.1700
Data Index: 5934050 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1364. Min Range: -6.1364
Max Act: 5.6677. Min Act: -0.1700
Data Index: 5235813 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1364. Min Range: -6.1364
Max Act: 5.6052. Min Act: -0.1700
Data Index: 5909042 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1364. Min Range: -6.1364
Max Act: 5.6052. Min Act: -0.1700
Data Index: 7717941 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1364. Min Range: -6.1364
Max Act: 5.6052. Min Act: -0.1700
Data Index: 82744 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1364. Min Range: -6.1364
Max Act: 5.5739. Min Act: -0.1700
Data Index: 5661036 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1364. Min Range: -6.1364
Max Act: 5.5739. Min Act: -0.1700
Data Index: 1287379 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #19