Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2908 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3421. Min Range: -6.3421
Max Act: 6.3421. Min Act: -0.1700
Data Index: 7730338 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3421. Min Range: -6.3421
Max Act: 6.3108. Min Act: -0.1700
Data Index: 3035241 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3421. Min Range: -6.3421
Max Act: 6.2171. Min Act: -0.1700
Data Index: 4769650 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3421. Min Range: -6.3421
Max Act: 6.2171. Min Act: -0.1700
Data Index: 7317993 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3421. Min Range: -6.3421
Max Act: 6.2171. Min Act: -0.1700
Data Index: 3859282 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3421. Min Range: -6.3421
Max Act: 6.1858. Min Act: -0.1700
Data Index: 4167126 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3421. Min Range: -6.3421
Max Act: 6.1233. Min Act: -0.1700
Data Index: 4564855 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3421. Min Range: -6.3421
Max Act: 6.1233. Min Act: -0.1700
Data Index: 3465427 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3421. Min Range: -6.3421
Max Act: 6.1233. Min Act: -0.1700
Data Index: 7555800 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3421. Min Range: -6.3421
Max Act: 6.0921. Min Act: -0.1700
Data Index: 2850319 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3421. Min Range: -6.3421
Max Act: 6.0921. Min Act: -0.1700
Data Index: 532972 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3421. Min Range: -6.3421
Max Act: 6.0608. Min Act: -0.1700
Data Index: 4607076 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3421. Min Range: -6.3421
Max Act: 6.0296. Min Act: -0.1700
Data Index: 8229510 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3421. Min Range: -6.3421
Max Act: 5.9983. Min Act: -0.1700
Data Index: 3671935 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3421. Min Range: -6.3421
Max Act: 5.9983. Min Act: -0.1700
Data Index: 3194539 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3421. Min Range: -6.3421
Max Act: 5.9983. Min Act: -0.1700
Data Index: 4576561 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3421. Min Range: -6.3421
Max Act: 5.9671. Min Act: -0.1700
Data Index: 7438736 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3421. Min Range: -6.3421
Max Act: 5.9671. Min Act: -0.1700
Data Index: 105335 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3421. Min Range: -6.3421
Max Act: 5.9671. Min Act: -0.1700
Data Index: 2512387 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3421. Min Range: -6.3421
Max Act: 5.9671. Min Act: -0.1700
Data Index: 6156526 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19