Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 802 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7612. Min Range: -6.7612
Max Act: 6.7612. Min Act: -0.1700
Data Index: 3858617 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7612. Min Range: -6.7612
Max Act: 6.6675. Min Act: -0.1700
Data Index: 2243475 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7612. Min Range: -6.7612
Max Act: 6.5425. Min Act: -0.1700
Data Index: 6233823 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7612. Min Range: -6.7612
Max Act: 6.4175. Min Act: -0.1700
Data Index: 1133263 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7612. Min Range: -6.7612
Max Act: 6.3550. Min Act: -0.1700
Data Index: 5470329 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7612. Min Range: -6.7612
Max Act: 6.2925. Min Act: -0.1700
Data Index: 8723043 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7612. Min Range: -6.7612
Max Act: 6.2925. Min Act: -0.1700
Data Index: 4625660 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7612. Min Range: -6.7612
Max Act: 6.1987. Min Act: -0.1700
Data Index: 459889 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7612. Min Range: -6.7612
Max Act: 6.1987. Min Act: -0.1700
Data Index: 7533447 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7612. Min Range: -6.7612
Max Act: 6.1987. Min Act: -0.1700
Data Index: 1915072 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7612. Min Range: -6.7612
Max Act: 6.1675. Min Act: -0.1700
Data Index: 1946381 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7612. Min Range: -6.7612
Max Act: 6.1362. Min Act: -0.1700
Data Index: 8725689 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7612. Min Range: -6.7612
Max Act: 6.1362. Min Act: -0.1700
Data Index: 8098229 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7612. Min Range: -6.7612
Max Act: 6.1362. Min Act: -0.1700
Data Index: 6723477 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7612. Min Range: -6.7612
Max Act: 6.1050. Min Act: -0.1700
Data Index: 4874209 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7612. Min Range: -6.7612
Max Act: 6.1050. Min Act: -0.1700
Data Index: 4619030 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7612. Min Range: -6.7612
Max Act: 6.1362. Min Act: -0.1700
Data Index: 7486248 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7612. Min Range: -6.7612
Max Act: 6.1050. Min Act: -0.1700
Data Index: 4437045 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7612. Min Range: -6.7612
Max Act: 6.0737. Min Act: -0.1700
Data Index: 3444166 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7612. Min Range: -6.7612
Max Act: 6.0737. Min Act: -0.1700
Data Index: 1207881 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19