Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4838 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0778. Min Range: -6.0778
Max Act: 6.0778. Min Act: -0.1700
Data Index: 6547949 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0778. Min Range: -6.0778
Max Act: 5.7966. Min Act: -0.1700
Data Index: 8512265 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0778. Min Range: -6.0778
Max Act: 5.4528. Min Act: -0.1700
Data Index: 2866559 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0778. Min Range: -6.0778
Max Act: 5.3278. Min Act: -0.1700
Data Index: 2866558 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0778. Min Range: -6.0778
Max Act: 5.3591. Min Act: -0.1700
Data Index: 8279351 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0778. Min Range: -6.0778
Max Act: 5.3591. Min Act: -0.1700
Data Index: 1515486 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0778. Min Range: -6.0778
Max Act: 5.3278. Min Act: -0.1700
Data Index: 2377438 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0778. Min Range: -6.0778
Max Act: 5.3278. Min Act: -0.1700
Data Index: 1927429 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0778. Min Range: -6.0778
Max Act: 5.3278. Min Act: -0.1700
Data Index: 6996190 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0778. Min Range: -6.0778
Max Act: 5.2966. Min Act: -0.1700
Data Index: 4360603 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0778. Min Range: -6.0778
Max Act: 5.3278. Min Act: -0.1700
Data Index: 6755546 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0778. Min Range: -6.0778
Max Act: 5.2966. Min Act: -0.1700
Data Index: 595132 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0778. Min Range: -6.0778
Max Act: 5.2653. Min Act: -0.1700
Data Index: 2025697 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0778. Min Range: -6.0778
Max Act: 5.2653. Min Act: -0.1700
Data Index: 6022069 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0778. Min Range: -6.0778
Max Act: 5.2653. Min Act: -0.1700
Data Index: 8640122 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0778. Min Range: -6.0778
Max Act: 5.2653. Min Act: -0.1700
Data Index: 558431 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0778. Min Range: -6.0778
Max Act: 5.2341. Min Act: -0.1700
Data Index: 7295049 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0778. Min Range: -6.0778
Max Act: 5.2341. Min Act: -0.1700
Data Index: 2546122 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0778. Min Range: -6.0778
Max Act: 5.2341. Min Act: -0.1700
Data Index: 8098979 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0778. Min Range: -6.0778
Max Act: 5.2341. Min Act: -0.1700
Data Index: 5842039 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19