Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2304 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2281. Min Range: -5.2281
Max Act: 5.2281. Min Act: -0.1700
Data Index: 8238132 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2281. Min Range: -5.2281
Max Act: 5.1656. Min Act: -0.1700
Data Index: 7265674 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2281. Min Range: -5.2281
Max Act: 5.1343. Min Act: -0.1700
Data Index: 4863070 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2281. Min Range: -5.2281
Max Act: 5.0718. Min Act: -0.1700
Data Index: 7357371 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2281. Min Range: -5.2281
Max Act: 5.0718. Min Act: -0.1700
Data Index: 8468454 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2281. Min Range: -5.2281
Max Act: 5.0718. Min Act: -0.1700
Data Index: 5244743 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2281. Min Range: -5.2281
Max Act: 5.1031. Min Act: -0.1700
Data Index: 4585275 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2281. Min Range: -5.2281
Max Act: 5.0406. Min Act: -0.1700
Data Index: 6802356 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2281. Min Range: -5.2281
Max Act: 5.0406. Min Act: -0.1700
Data Index: 4311214 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2281. Min Range: -5.2281
Max Act: 5.0406. Min Act: -0.1700
Data Index: 7275705 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2281. Min Range: -5.2281
Max Act: 5.0406. Min Act: -0.1700
Data Index: 2464480 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2281. Min Range: -5.2281
Max Act: 5.0093. Min Act: -0.1700
Data Index: 4828111 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2281. Min Range: -5.2281
Max Act: 5.0093. Min Act: -0.1700
Data Index: 7410071 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.9781. Min Act: -0.1700
Data Index: 8542336 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.9781. Min Act: -0.1700
Data Index: 3052877 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.9781. Min Act: -0.1700
Data Index: 8091656 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.9781. Min Act: -0.1700
Data Index: 2794625 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.9468. Min Act: -0.1700
Data Index: 1311189 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.9468. Min Act: -0.1700
Data Index: 6046678 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.9781. Min Act: -0.1700
Data Index: 267055 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19