Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 990 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8187. Min Range: -7.8187
Max Act: 7.8187. Min Act: -0.1700
Data Index: 8768233 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8187. Min Range: -7.8187
Max Act: 7.7562. Min Act: -0.1700
Data Index: 5371386 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8187. Min Range: -7.8187
Max Act: 7.6312. Min Act: -0.1700
Data Index: 7282878 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8187. Min Range: -7.8187
Max Act: 7.5999. Min Act: -0.1700
Data Index: 8279067 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8187. Min Range: -7.8187
Max Act: 7.6624. Min Act: -0.1700
Data Index: 7693150 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8187. Min Range: -7.8187
Max Act: 7.6312. Min Act: -0.1700
Data Index: 4111370 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8187. Min Range: -7.8187
Max Act: 7.6312. Min Act: -0.1700
Data Index: 5701121 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8187. Min Range: -7.8187
Max Act: 7.5999. Min Act: -0.1700
Data Index: 2791149 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8187. Min Range: -7.8187
Max Act: 7.5999. Min Act: -0.1700
Data Index: 3684319 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8187. Min Range: -7.8187
Max Act: 7.5999. Min Act: -0.1700
Data Index: 4023044 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8187. Min Range: -7.8187
Max Act: 7.5374. Min Act: -0.1700
Data Index: 3169613 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8187. Min Range: -7.8187
Max Act: 7.5062. Min Act: -0.1700
Data Index: 3696946 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8187. Min Range: -7.8187
Max Act: 7.4749. Min Act: -0.1700
Data Index: 1576735 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8187. Min Range: -7.8187
Max Act: 7.4749. Min Act: -0.1700
Data Index: 1389852 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8187. Min Range: -7.8187
Max Act: 7.4437. Min Act: -0.1700
Data Index: 3046793 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8187. Min Range: -7.8187
Max Act: 7.4124. Min Act: -0.1700
Data Index: 7094055 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8187. Min Range: -7.8187
Max Act: 7.3812. Min Act: -0.1700
Data Index: 6447609 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8187. Min Range: -7.8187
Max Act: 7.3499. Min Act: -0.1700
Data Index: 4483146 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8187. Min Range: -7.8187
Max Act: 7.4124. Min Act: -0.1700
Data Index: 5398449 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8187. Min Range: -7.8187
Max Act: 7.3812. Min Act: -0.1700
Data Index: 6174965 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #19