Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4999 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1560. Min Range: -4.1560
Max Act: 4.1560. Min Act: -0.1700
Data Index: 6305293 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1560. Min Range: -4.1560
Max Act: 4.0934. Min Act: -0.1700
Data Index: 2747065 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1560. Min Range: -4.1560
Max Act: 4.0622. Min Act: -0.1700
Data Index: 3113943 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1560. Min Range: -4.1560
Max Act: 4.0622. Min Act: -0.1700
Data Index: 3310842 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1560. Min Range: -4.1560
Max Act: 4.0309. Min Act: -0.1700
Data Index: 2144739 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1560. Min Range: -4.1560
Max Act: 4.0309. Min Act: -0.1700
Data Index: 3391113 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1560. Min Range: -4.1560
Max Act: 3.9997. Min Act: -0.1700
Data Index: 5072068 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1560. Min Range: -4.1560
Max Act: 3.9684. Min Act: -0.1700
Data Index: 4042862 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1560. Min Range: -4.1560
Max Act: 3.9684. Min Act: -0.1700
Data Index: 1006523 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1560. Min Range: -4.1560
Max Act: 3.9371. Min Act: -0.1700
Data Index: 894140 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1560. Min Range: -4.1560
Max Act: 3.9371. Min Act: -0.1700
Data Index: 2296160 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1560. Min Range: -4.1560
Max Act: 3.9371. Min Act: -0.1700
Data Index: 5072069 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1560. Min Range: -4.1560
Max Act: 3.9059. Min Act: -0.1700
Data Index: 6407373 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1560. Min Range: -4.1560
Max Act: 3.8433. Min Act: -0.1700
Data Index: 854324 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1560. Min Range: -4.1560
Max Act: 3.8746. Min Act: -0.1700
Data Index: 499886 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1560. Min Range: -4.1560
Max Act: 3.8433. Min Act: -0.1700
Data Index: 1490096 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1560. Min Range: -4.1560
Max Act: 3.8433. Min Act: -0.1700
Data Index: 8651003 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1560. Min Range: -4.1560
Max Act: 3.8433. Min Act: -0.1700
Data Index: 8454295 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1560. Min Range: -4.1560
Max Act: 3.7808. Min Act: -0.1700
Data Index: 891870 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1560. Min Range: -4.1560
Max Act: 3.8433. Min Act: -0.1700
Data Index: 5219248 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #19