Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2973 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7857. Min Range: -6.7857
Max Act: 6.7857. Min Act: -0.1700
Data Index: 6267426 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7857. Min Range: -6.7857
Max Act: 6.6607. Min Act: -0.1700
Data Index: 8377355 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7857. Min Range: -6.7857
Max Act: 6.6294. Min Act: -0.1700
Data Index: 3316271 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7857. Min Range: -6.7857
Max Act: 6.5044. Min Act: -0.1700
Data Index: 5991885 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7857. Min Range: -6.7857
Max Act: 6.4107. Min Act: -0.1700
Data Index: 2808890 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7857. Min Range: -6.7857
Max Act: 6.3794. Min Act: -0.1700
Data Index: 2199053 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7857. Min Range: -6.7857
Max Act: 6.3482. Min Act: -0.1700
Data Index: 3504935 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7857. Min Range: -6.7857
Max Act: 6.3169. Min Act: -0.1700
Data Index: 7436530 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7857. Min Range: -6.7857
Max Act: 6.3169. Min Act: -0.1700
Data Index: 3813873 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7857. Min Range: -6.7857
Max Act: 6.2857. Min Act: -0.1700
Data Index: 6378193 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7857. Min Range: -6.7857
Max Act: 6.2857. Min Act: -0.1700
Data Index: 3806318 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7857. Min Range: -6.7857
Max Act: 6.2544. Min Act: -0.1700
Data Index: 6787190 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7857. Min Range: -6.7857
Max Act: 6.2232. Min Act: -0.1700
Data Index: 3219602 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7857. Min Range: -6.7857
Max Act: 6.1919. Min Act: -0.1700
Data Index: 630456 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7857. Min Range: -6.7857
Max Act: 6.1607. Min Act: -0.1700
Data Index: 7903776 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7857. Min Range: -6.7857
Max Act: 6.1919. Min Act: -0.1700
Data Index: 4627360 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7857. Min Range: -6.7857
Max Act: 6.1294. Min Act: -0.1700
Data Index: 5207442 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7857. Min Range: -6.7857
Max Act: 6.1607. Min Act: -0.1700
Data Index: 6454092 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7857. Min Range: -6.7857
Max Act: 6.1294. Min Act: -0.1700
Data Index: 5951361 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7857. Min Range: -6.7857
Max Act: 6.1294. Min Act: -0.1700
Data Index: 1624283 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19