Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1331 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.7418. Min Act: -0.1700
Data Index: 4126600 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.7578. Min Act: -0.1700
Data Index: 1596774 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.7258. Min Act: -0.1700
Data Index: 363481 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.6938. Min Act: -0.1700
Data Index: 6640788 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.5975. Min Act: -0.1700
Data Index: 4080042 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.5975. Min Act: -0.1700
Data Index: 5806580 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.5975. Min Act: -0.1700
Data Index: 4080044 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.5492. Min Act: -0.1700
Data Index: 2477891 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.5330. Min Act: -0.1700
Data Index: 5134720 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.5330. Min Act: -0.1700
Data Index: 4622380 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.5168. Min Act: -0.1700
Data Index: 8499926 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.5006. Min Act: -0.1700
Data Index: 4940645 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.4844. Min Act: -0.1700
Data Index: 4058983 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.4520. Min Act: -0.1700
Data Index: 5806583 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.4357. Min Act: -0.1700
Data Index: 4924078 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.4357. Min Act: -0.1700
Data Index: 3276888 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.4357. Min Act: -0.1700
Data Index: 5026672 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.4357. Min Act: -0.1700
Data Index: 4239075 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.4194. Min Act: -0.1700
Data Index: 3384384 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7578. Min Range: -2.7578
Max Act: 2.4194. Min Act: -0.1700
Data Index: 1023174 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19