Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1900 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3907. Min Range: -9.3907
Max Act: 9.3907. Min Act: -0.1700
Data Index: 6430117 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3907. Min Range: -9.3907
Max Act: 9.2657. Min Act: -0.1700
Data Index: 2796089 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3907. Min Range: -9.3907
Max Act: 9.1407. Min Act: -0.1700
Data Index: 3205017 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3907. Min Range: -9.3907
Max Act: 9.1407. Min Act: -0.1700
Data Index: 7650563 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3907. Min Range: -9.3907
Max Act: 9.0782. Min Act: -0.1700
Data Index: 6731907 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3907. Min Range: -9.3907
Max Act: 9.0782. Min Act: -0.1700
Data Index: 7041818 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3907. Min Range: -9.3907
Max Act: 8.8907. Min Act: -0.1700
Data Index: 2270766 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3907. Min Range: -9.3907
Max Act: 8.8907. Min Act: -0.1700
Data Index: 7816410 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3907. Min Range: -9.3907
Max Act: 8.8282. Min Act: -0.1700
Data Index: 4920153 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3907. Min Range: -9.3907
Max Act: 8.8907. Min Act: -0.1700
Data Index: 1401763 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3907. Min Range: -9.3907
Max Act: 8.7657. Min Act: -0.1700
Data Index: 8460519 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3907. Min Range: -9.3907
Max Act: 8.7657. Min Act: -0.1700
Data Index: 5960232 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3907. Min Range: -9.3907
Max Act: 8.7032. Min Act: -0.1700
Data Index: 3531478 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3907. Min Range: -9.3907
Max Act: 8.6407. Min Act: -0.1700
Data Index: 571237 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3907. Min Range: -9.3907
Max Act: 8.6407. Min Act: -0.1700
Data Index: 1989762 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3907. Min Range: -9.3907
Max Act: 8.6407. Min Act: -0.1700
Data Index: 7528147 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3907. Min Range: -9.3907
Max Act: 8.6407. Min Act: -0.1700
Data Index: 944248 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3907. Min Range: -9.3907
Max Act: 8.5782. Min Act: -0.1700
Data Index: 7131412 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3907. Min Range: -9.3907
Max Act: 8.5782. Min Act: -0.1700
Data Index: 7731908 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3907. Min Range: -9.3907
Max Act: 8.5157. Min Act: -0.1699
Data Index: 4059675 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #19