Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2557 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5364. Min Range: -5.5364
Max Act: 5.5364. Min Act: -0.1700
Data Index: 875098 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5364. Min Range: -5.5364
Max Act: 5.1926. Min Act: -0.1700
Data Index: 2391361 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5364. Min Range: -5.5364
Max Act: 5.1614. Min Act: -0.1700
Data Index: 6410055 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5364. Min Range: -5.5364
Max Act: 5.1301. Min Act: -0.1700
Data Index: 659151 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5364. Min Range: -5.5364
Max Act: 5.1301. Min Act: -0.1700
Data Index: 6335641 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5364. Min Range: -5.5364
Max Act: 5.1301. Min Act: -0.1700
Data Index: 1105065 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5364. Min Range: -5.5364
Max Act: 5.0989. Min Act: -0.1700
Data Index: 3683164 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5364. Min Range: -5.5364
Max Act: 5.1301. Min Act: -0.1700
Data Index: 1619958 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5364. Min Range: -5.5364
Max Act: 5.1301. Min Act: -0.1700
Data Index: 1625457 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5364. Min Range: -5.5364
Max Act: 5.0676. Min Act: -0.1700
Data Index: 5130106 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5364. Min Range: -5.5364
Max Act: 5.0676. Min Act: -0.1700
Data Index: 1465315 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5364. Min Range: -5.5364
Max Act: 5.0676. Min Act: -0.1700
Data Index: 6804729 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5364. Min Range: -5.5364
Max Act: 5.0364. Min Act: -0.1700
Data Index: 5846024 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5364. Min Range: -5.5364
Max Act: 5.0364. Min Act: -0.1700
Data Index: 6794327 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5364. Min Range: -5.5364
Max Act: 5.0364. Min Act: -0.1700
Data Index: 1241936 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5364. Min Range: -5.5364
Max Act: 5.0051. Min Act: -0.1700
Data Index: 7141702 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5364. Min Range: -5.5364
Max Act: 5.0364. Min Act: -0.1700
Data Index: 88218 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5364. Min Range: -5.5364
Max Act: 5.0051. Min Act: -0.1700
Data Index: 2689378 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5364. Min Range: -5.5364
Max Act: 5.0051. Min Act: -0.1700
Data Index: 1378122 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5364. Min Range: -5.5364
Max Act: 5.0051. Min Act: -0.1700
Data Index: 4433628 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19