Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3968 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4218. Min Range: -8.4218
Max Act: 8.4218. Min Act: -0.1700
Data Index: 1871830 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4218. Min Range: -8.4218
Max Act: 7.2343. Min Act: -0.1700
Data Index: 7800844 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4218. Min Range: -8.4218
Max Act: 7.2343. Min Act: -0.1700
Data Index: 8257000 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4218. Min Range: -8.4218
Max Act: 7.2343. Min Act: -0.1700
Data Index: 6552756 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4218. Min Range: -8.4218
Max Act: 7.1406. Min Act: -0.1700
Data Index: 5901138 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4218. Min Range: -8.4218
Max Act: 7.1093. Min Act: -0.1700
Data Index: 8242169 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4218. Min Range: -8.4218
Max Act: 7.0468. Min Act: -0.1700
Data Index: 2630889 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4218. Min Range: -8.4218
Max Act: 7.0156. Min Act: -0.1700
Data Index: 4844969 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4218. Min Range: -8.4218
Max Act: 7.0468. Min Act: -0.1700
Data Index: 4025591 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4218. Min Range: -8.4218
Max Act: 7.0156. Min Act: -0.1700
Data Index: 3593331 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4218. Min Range: -8.4218
Max Act: 6.9531. Min Act: -0.1700
Data Index: 831333 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4218. Min Range: -8.4218
Max Act: 6.9531. Min Act: -0.1700
Data Index: 7762470 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4218. Min Range: -8.4218
Max Act: 6.9218. Min Act: -0.1700
Data Index: 7312520 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4218. Min Range: -8.4218
Max Act: 6.8593. Min Act: -0.1700
Data Index: 1075451 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4218. Min Range: -8.4218
Max Act: 6.8281. Min Act: -0.1700
Data Index: 2332376 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4218. Min Range: -8.4218
Max Act: 6.8281. Min Act: -0.1700
Data Index: 4570764 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4218. Min Range: -8.4218
Max Act: 6.7968. Min Act: -0.1700
Data Index: 1784091 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4218. Min Range: -8.4218
Max Act: 6.8281. Min Act: -0.1700
Data Index: 4627681 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4218. Min Range: -8.4218
Max Act: 6.7968. Min Act: -0.1700
Data Index: 2566468 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4218. Min Range: -8.4218
Max Act: 6.7968. Min Act: -0.1700
Data Index: 4606528 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19