Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1586 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5214. Min Range: -6.5214
Max Act: 6.5214. Min Act: -0.1700
Data Index: 3339940 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5214. Min Range: -6.5214
Max Act: 6.3964. Min Act: -0.1700
Data Index: 6021480 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5214. Min Range: -6.5214
Max Act: 6.3652. Min Act: -0.1700
Data Index: 7713122 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5214. Min Range: -6.5214
Max Act: 6.2714. Min Act: -0.1700
Data Index: 4471275 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5214. Min Range: -6.5214
Max Act: 6.2089. Min Act: -0.1700
Data Index: 6886953 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5214. Min Range: -6.5214
Max Act: 6.1777. Min Act: -0.1700
Data Index: 7749382 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5214. Min Range: -6.5214
Max Act: 6.1464. Min Act: -0.1700
Data Index: 7592358 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5214. Min Range: -6.5214
Max Act: 6.0839. Min Act: -0.1700
Data Index: 544410 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5214. Min Range: -6.5214
Max Act: 6.0839. Min Act: -0.1700
Data Index: 568309 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5214. Min Range: -6.5214
Max Act: 6.0839. Min Act: -0.1700
Data Index: 1637788 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5214. Min Range: -6.5214
Max Act: 6.0839. Min Act: -0.1700
Data Index: 3310053 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5214. Min Range: -6.5214
Max Act: 6.0839. Min Act: -0.1700
Data Index: 6917175 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5214. Min Range: -6.5214
Max Act: 6.0527. Min Act: -0.1700
Data Index: 6646043 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5214. Min Range: -6.5214
Max Act: 6.0527. Min Act: -0.1700
Data Index: 206094 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5214. Min Range: -6.5214
Max Act: 6.0527. Min Act: -0.1700
Data Index: 3918818 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5214. Min Range: -6.5214
Max Act: 6.0527. Min Act: -0.1700
Data Index: 321887 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5214. Min Range: -6.5214
Max Act: 5.9902. Min Act: -0.1700
Data Index: 8454091 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5214. Min Range: -6.5214
Max Act: 6.0214. Min Act: -0.1700
Data Index: 6623165 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5214. Min Range: -6.5214
Max Act: 6.0214. Min Act: -0.1700
Data Index: 2265911 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5214. Min Range: -6.5214
Max Act: 5.9902. Min Act: -0.1700
Data Index: 4690190 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19