Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1422 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3106. Min Range: -6.3106
Max Act: 6.3106. Min Act: -0.1700
Data Index: 3468539 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3106. Min Range: -6.3106
Max Act: 6.2169. Min Act: -0.1700
Data Index: 6000413 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3106. Min Range: -6.3106
Max Act: 6.1856. Min Act: -0.1700
Data Index: 6000411 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3106. Min Range: -6.3106
Max Act: 6.2169. Min Act: -0.1700
Data Index: 6616120 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3106. Min Range: -6.3106
Max Act: 6.1231. Min Act: -0.1700
Data Index: 1763825 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3106. Min Range: -6.3106
Max Act: 6.0606. Min Act: -0.1700
Data Index: 1929584 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3106. Min Range: -6.3106
Max Act: 6.0919. Min Act: -0.1700
Data Index: 1669762 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3106. Min Range: -6.3106
Max Act: 6.0606. Min Act: -0.1700
Data Index: 1275159 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3106. Min Range: -6.3106
Max Act: 6.0606. Min Act: -0.1700
Data Index: 5699755 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3106. Min Range: -6.3106
Max Act: 6.0294. Min Act: -0.1700
Data Index: 4034321 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3106. Min Range: -6.3106
Max Act: 5.9981. Min Act: -0.1700
Data Index: 7039044 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3106. Min Range: -6.3106
Max Act: 5.9981. Min Act: -0.1700
Data Index: 1235690 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3106. Min Range: -6.3106
Max Act: 5.9669. Min Act: -0.1700
Data Index: 1357320 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3106. Min Range: -6.3106
Max Act: 5.9669. Min Act: -0.1700
Data Index: 2932027 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3106. Min Range: -6.3106
Max Act: 5.9356. Min Act: -0.1700
Data Index: 5702140 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3106. Min Range: -6.3106
Max Act: 5.8731. Min Act: -0.1700
Data Index: 6158708 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3106. Min Range: -6.3106
Max Act: 5.9044. Min Act: -0.1700
Data Index: 4553965 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3106. Min Range: -6.3106
Max Act: 5.9044. Min Act: -0.1700
Data Index: 91789 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3106. Min Range: -6.3106
Max Act: 5.8731. Min Act: -0.1700
Data Index: 1033431 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3106. Min Range: -6.3106
Max Act: 5.8731. Min Act: -0.1700
Data Index: 3500550 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19