Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3410 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0498. Min Range: -5.0498
Max Act: 5.0498. Min Act: -0.1700
Data Index: 5036942 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0498. Min Range: -5.0498
Max Act: 5.0498. Min Act: -0.1700
Data Index: 7945504 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0498. Min Range: -5.0498
Max Act: 5.0498. Min Act: -0.1700
Data Index: 177498 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0498. Min Range: -5.0498
Max Act: 5.0185. Min Act: -0.1700
Data Index: 1714548 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0498. Min Range: -5.0498
Max Act: 4.9873. Min Act: -0.1700
Data Index: 3271477 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0498. Min Range: -5.0498
Max Act: 5.0185. Min Act: -0.1700
Data Index: 3542809 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0498. Min Range: -5.0498
Max Act: 4.9560. Min Act: -0.1700
Data Index: 4214837 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0498. Min Range: -5.0498
Max Act: 4.9873. Min Act: -0.1700
Data Index: 7098818 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0498. Min Range: -5.0498
Max Act: 4.9560. Min Act: -0.1700
Data Index: 841351 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0498. Min Range: -5.0498
Max Act: 4.9560. Min Act: -0.1700
Data Index: 7735135 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0498. Min Range: -5.0498
Max Act: 4.9560. Min Act: -0.1700
Data Index: 7832304 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0498. Min Range: -5.0498
Max Act: 4.9248. Min Act: -0.1700
Data Index: 6991515 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0498. Min Range: -5.0498
Max Act: 4.8935. Min Act: -0.1700
Data Index: 2833978 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0498. Min Range: -5.0498
Max Act: 4.9248. Min Act: -0.1700
Data Index: 8243225 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0498. Min Range: -5.0498
Max Act: 4.9248. Min Act: -0.1700
Data Index: 1168514 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0498. Min Range: -5.0498
Max Act: 4.9248. Min Act: -0.1700
Data Index: 3092775 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0498. Min Range: -5.0498
Max Act: 4.9248. Min Act: -0.1700
Data Index: 958831 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0498. Min Range: -5.0498
Max Act: 4.9248. Min Act: -0.1700
Data Index: 927457 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0498. Min Range: -5.0498
Max Act: 4.8935. Min Act: -0.1700
Data Index: 4506057 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0498. Min Range: -5.0498
Max Act: 4.8623. Min Act: -0.1700
Data Index: 6868067 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #19