Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5419 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6466. Min Range: -10.6466
Max Act: 10.6466. Min Act: -0.1700
Data Index: 7774271 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6466. Min Range: -10.6466
Max Act: 10.5841. Min Act: -0.1700
Data Index: 2203480 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6466. Min Range: -10.6466
Max Act: 10.4591. Min Act: -0.1700
Data Index: 5069244 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6466. Min Range: -10.6466
Max Act: 10.3341. Min Act: -0.1700
Data Index: 1087202 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6466. Min Range: -10.6466
Max Act: 10.3341. Min Act: -0.1700
Data Index: 4819233 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6466. Min Range: -10.6466
Max Act: 10.2716. Min Act: -0.1700
Data Index: 6108029 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6466. Min Range: -10.6466
Max Act: 10.3341. Min Act: -0.1700
Data Index: 5553782 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6466. Min Range: -10.6466
Max Act: 10.2716. Min Act: -0.1700
Data Index: 7755912 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6466. Min Range: -10.6466
Max Act: 10.2091. Min Act: -0.1700
Data Index: 7632895 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6466. Min Range: -10.6466
Max Act: 10.2091. Min Act: -0.1700
Data Index: 5963892 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6466. Min Range: -10.6466
Max Act: 10.1466. Min Act: -0.1700
Data Index: 4642520 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6466. Min Range: -10.6466
Max Act: 10.1466. Min Act: -0.1700
Data Index: 7444097 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6466. Min Range: -10.6466
Max Act: 10.1466. Min Act: -0.1700
Data Index: 7753151 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6466. Min Range: -10.6466
Max Act: 10.0841. Min Act: -0.1700
Data Index: 2870408 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6466. Min Range: -10.6466
Max Act: 10.0841. Min Act: -0.1700
Data Index: 5466444 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6466. Min Range: -10.6466
Max Act: 10.0841. Min Act: -0.1700
Data Index: 5618161 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6466. Min Range: -10.6466
Max Act: 10.0841. Min Act: -0.1700
Data Index: 191742 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6466. Min Range: -10.6466
Max Act: 10.0841. Min Act: -0.1700
Data Index: 7708005 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6466. Min Range: -10.6466
Max Act: 10.0841. Min Act: -0.1700
Data Index: 6716769 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6466. Min Range: -10.6466
Max Act: 10.0841. Min Act: -0.1700
Data Index: 1927943 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #19