Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1844 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4464. Min Range: -6.4464
Max Act: 6.4464. Min Act: -0.1700
Data Index: 5007300 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4464. Min Range: -6.4464
Max Act: 6.3839. Min Act: -0.1700
Data Index: 5866508 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4464. Min Range: -6.4464
Max Act: 6.2276. Min Act: -0.1700
Data Index: 1982456 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4464. Min Range: -6.4464
Max Act: 6.1964. Min Act: -0.1700
Data Index: 2585612 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4464. Min Range: -6.4464
Max Act: 6.1964. Min Act: -0.1700
Data Index: 4713527 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4464. Min Range: -6.4464
Max Act: 6.1026. Min Act: -0.1700
Data Index: 284319 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4464. Min Range: -6.4464
Max Act: 6.1026. Min Act: -0.1700
Data Index: 3522941 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4464. Min Range: -6.4464
Max Act: 6.0714. Min Act: -0.1700
Data Index: 2149614 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4464. Min Range: -6.4464
Max Act: 6.0401. Min Act: -0.1700
Data Index: 2564746 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4464. Min Range: -6.4464
Max Act: 6.0089. Min Act: -0.1700
Data Index: 7886013 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4464. Min Range: -6.4464
Max Act: 6.0089. Min Act: -0.1700
Data Index: 7049002 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4464. Min Range: -6.4464
Max Act: 6.0089. Min Act: -0.1700
Data Index: 3533092 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4464. Min Range: -6.4464
Max Act: 5.9464. Min Act: -0.1700
Data Index: 1062644 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4464. Min Range: -6.4464
Max Act: 5.9464. Min Act: -0.1700
Data Index: 6211570 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4464. Min Range: -6.4464
Max Act: 5.9464. Min Act: -0.1700
Data Index: 7458852 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4464. Min Range: -6.4464
Max Act: 5.9464. Min Act: -0.1700
Data Index: 155311 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4464. Min Range: -6.4464
Max Act: 5.9464. Min Act: -0.1700
Data Index: 4016974 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4464. Min Range: -6.4464
Max Act: 5.9151. Min Act: -0.1700
Data Index: 2731503 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4464. Min Range: -6.4464
Max Act: 5.8526. Min Act: -0.1700
Data Index: 1543525 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4464. Min Range: -6.4464
Max Act: 5.8526. Min Act: -0.1700
Data Index: 7009314 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #19