Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1631 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0074. Min Range: -8.0074
Max Act: 8.0074. Min Act: -0.1700
Data Index: 669091 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0074. Min Range: -8.0074
Max Act: 7.8824. Min Act: -0.1700
Data Index: 5462767 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0074. Min Range: -8.0074
Max Act: 7.5387. Min Act: -0.1700
Data Index: 3604464 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0074. Min Range: -8.0074
Max Act: 7.5387. Min Act: -0.1700
Data Index: 926085 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0074. Min Range: -8.0074
Max Act: 7.4449. Min Act: -0.1700
Data Index: 6615536 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0074. Min Range: -8.0074
Max Act: 7.4137. Min Act: -0.1700
Data Index: 3501203 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0074. Min Range: -8.0074
Max Act: 7.3824. Min Act: -0.1700
Data Index: 6731848 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0074. Min Range: -8.0074
Max Act: 7.3824. Min Act: -0.1700
Data Index: 2287896 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0074. Min Range: -8.0074
Max Act: 7.3824. Min Act: -0.1700
Data Index: 7935886 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0074. Min Range: -8.0074
Max Act: 7.3199. Min Act: -0.1700
Data Index: 433971 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0074. Min Range: -8.0074
Max Act: 7.3199. Min Act: -0.1700
Data Index: 874799 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0074. Min Range: -8.0074
Max Act: 7.2887. Min Act: -0.1700
Data Index: 4009743 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0074. Min Range: -8.0074
Max Act: 7.2574. Min Act: -0.1700
Data Index: 3731035 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0074. Min Range: -8.0074
Max Act: 7.1949. Min Act: -0.1700
Data Index: 6942333 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0074. Min Range: -8.0074
Max Act: 7.1637. Min Act: -0.1700
Data Index: 1133178 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0074. Min Range: -8.0074
Max Act: 7.1637. Min Act: -0.1700
Data Index: 877332 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0074. Min Range: -8.0074
Max Act: 7.1949. Min Act: -0.1700
Data Index: 1355637 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0074. Min Range: -8.0074
Max Act: 7.1324. Min Act: -0.1700
Data Index: 6330063 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0074. Min Range: -8.0074
Max Act: 7.1012. Min Act: -0.1700
Data Index: 6450854 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0074. Min Range: -8.0074
Max Act: 7.1324. Min Act: -0.1700
Data Index: 390632 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #19