Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3135 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8744. Min Range: -6.8744
Max Act: 6.8744. Min Act: -0.1700
Data Index: 2266920 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8744. Min Range: -6.8744
Max Act: 6.8432. Min Act: -0.1700
Data Index: 4528298 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8744. Min Range: -6.8744
Max Act: 6.8432. Min Act: -0.1700
Data Index: 3577772 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8744. Min Range: -6.8744
Max Act: 6.7182. Min Act: -0.1700
Data Index: 8189483 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8744. Min Range: -6.8744
Max Act: 6.6557. Min Act: -0.1700
Data Index: 442941 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8744. Min Range: -6.8744
Max Act: 6.5932. Min Act: -0.1700
Data Index: 8620307 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8744. Min Range: -6.8744
Max Act: 6.5932. Min Act: -0.1700
Data Index: 42887 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8744. Min Range: -6.8744
Max Act: 6.5619. Min Act: -0.1700
Data Index: 5658054 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8744. Min Range: -6.8744
Max Act: 6.5619. Min Act: -0.1700
Data Index: 3758106 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8744. Min Range: -6.8744
Max Act: 6.5619. Min Act: -0.1700
Data Index: 2574917 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8744. Min Range: -6.8744
Max Act: 6.5307. Min Act: -0.1700
Data Index: 55452 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8744. Min Range: -6.8744
Max Act: 6.4994. Min Act: -0.1700
Data Index: 1107619 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8744. Min Range: -6.8744
Max Act: 6.4994. Min Act: -0.1700
Data Index: 5811485 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8744. Min Range: -6.8744
Max Act: 6.4994. Min Act: -0.1700
Data Index: 6748687 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8744. Min Range: -6.8744
Max Act: 6.4682. Min Act: -0.1700
Data Index: 8398884 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8744. Min Range: -6.8744
Max Act: 6.4369. Min Act: -0.1700
Data Index: 519178 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8744. Min Range: -6.8744
Max Act: 6.4682. Min Act: -0.1700
Data Index: 262456 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8744. Min Range: -6.8744
Max Act: 6.4057. Min Act: -0.1700
Data Index: 3333697 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8744. Min Range: -6.8744
Max Act: 6.4057. Min Act: -0.1700
Data Index: 1315758 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8744. Min Range: -6.8744
Max Act: 6.4057. Min Act: -0.1700
Data Index: 5604362 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #19