Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 218 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0592. Min Range: -5.0592
Max Act: 5.0592. Min Act: -0.1700
Data Index: 3504275 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0592. Min Range: -5.0592
Max Act: 4.6217. Min Act: -0.1700
Data Index: 3634500 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0592. Min Range: -5.0592
Max Act: 4.5905. Min Act: -0.1700
Data Index: 598838 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0592. Min Range: -5.0592
Max Act: 4.5592. Min Act: -0.1700
Data Index: 8128221 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0592. Min Range: -5.0592
Max Act: 4.5280. Min Act: -0.1700
Data Index: 7084136 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0592. Min Range: -5.0592
Max Act: 4.4967. Min Act: -0.1700
Data Index: 4764802 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0592. Min Range: -5.0592
Max Act: 4.4967. Min Act: -0.1700
Data Index: 3454155 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0592. Min Range: -5.0592
Max Act: 4.4030. Min Act: -0.1700
Data Index: 1713091 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0592. Min Range: -5.0592
Max Act: 4.3717. Min Act: -0.1700
Data Index: 5424541 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0592. Min Range: -5.0592
Max Act: 4.3405. Min Act: -0.1700
Data Index: 6042911 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0592. Min Range: -5.0592
Max Act: 4.3405. Min Act: -0.1700
Data Index: 3930909 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0592. Min Range: -5.0592
Max Act: 4.3092. Min Act: -0.1700
Data Index: 6297270 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0592. Min Range: -5.0592
Max Act: 4.2467. Min Act: -0.1700
Data Index: 1404650 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0592. Min Range: -5.0592
Max Act: 4.2155. Min Act: -0.1700
Data Index: 5819207 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0592. Min Range: -5.0592
Max Act: 4.2155. Min Act: -0.1700
Data Index: 7251946 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0592. Min Range: -5.0592
Max Act: 4.1842. Min Act: -0.1700
Data Index: 2816672 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0592. Min Range: -5.0592
Max Act: 4.1842. Min Act: -0.1700
Data Index: 1651983 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0592. Min Range: -5.0592
Max Act: 4.1842. Min Act: -0.1700
Data Index: 5133020 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0592. Min Range: -5.0592
Max Act: 4.1842. Min Act: -0.1700
Data Index: 4662132 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0592. Min Range: -5.0592
Max Act: 4.1842. Min Act: -0.1700
Data Index: 1939192 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #19