Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 846 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2575. Min Range: -7.2575
Max Act: 7.2575. Min Act: -0.1700
Data Index: 5931075 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2575. Min Range: -7.2575
Max Act: 7.2575. Min Act: -0.1700
Data Index: 2328139 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2575. Min Range: -7.2575
Max Act: 7.0700. Min Act: -0.1700
Data Index: 7841109 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2575. Min Range: -7.2575
Max Act: 7.0387. Min Act: -0.1700
Data Index: 4477834 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2575. Min Range: -7.2575
Max Act: 7.0387. Min Act: -0.1700
Data Index: 1857154 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2575. Min Range: -7.2575
Max Act: 6.9450. Min Act: -0.1700
Data Index: 5369599 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2575. Min Range: -7.2575
Max Act: 6.9137. Min Act: -0.1700
Data Index: 2641707 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2575. Min Range: -7.2575
Max Act: 6.9137. Min Act: -0.1700
Data Index: 1062591 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2575. Min Range: -7.2575
Max Act: 6.8200. Min Act: -0.1700
Data Index: 8610408 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2575. Min Range: -7.2575
Max Act: 6.8200. Min Act: -0.1700
Data Index: 364481 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2575. Min Range: -7.2575
Max Act: 6.7887. Min Act: -0.1700
Data Index: 6775105 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2575. Min Range: -7.2575
Max Act: 6.7887. Min Act: -0.1700
Data Index: 4361183 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2575. Min Range: -7.2575
Max Act: 6.7887. Min Act: -0.1700
Data Index: 6394071 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2575. Min Range: -7.2575
Max Act: 6.7575. Min Act: -0.1700
Data Index: 7263527 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2575. Min Range: -7.2575
Max Act: 6.7575. Min Act: -0.1700
Data Index: 253787 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2575. Min Range: -7.2575
Max Act: 6.7575. Min Act: -0.1700
Data Index: 1394427 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2575. Min Range: -7.2575
Max Act: 6.7262. Min Act: -0.1700
Data Index: 5654057 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2575. Min Range: -7.2575
Max Act: 6.7262. Min Act: -0.1700
Data Index: 8019526 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2575. Min Range: -7.2575
Max Act: 6.7262. Min Act: -0.1700
Data Index: 4135634 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2575. Min Range: -7.2575
Max Act: 6.6950. Min Act: -0.1700
Data Index: 5850205 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19