Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 708 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4154. Min Range: -7.4154
Max Act: 7.4154. Min Act: -0.1700
Data Index: 2348390 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4154. Min Range: -7.4154
Max Act: 7.2904. Min Act: -0.1700
Data Index: 1693824 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4154. Min Range: -7.4154
Max Act: 7.2279. Min Act: -0.1700
Data Index: 1046414 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4154. Min Range: -7.4154
Max Act: 7.1654. Min Act: -0.1700
Data Index: 3494230 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4154. Min Range: -7.4154
Max Act: 7.1654. Min Act: -0.1700
Data Index: 8528756 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4154. Min Range: -7.4154
Max Act: 7.1029. Min Act: -0.1700
Data Index: 5246544 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4154. Min Range: -7.4154
Max Act: 7.0404. Min Act: -0.1700
Data Index: 6987351 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4154. Min Range: -7.4154
Max Act: 7.0092. Min Act: -0.1700
Data Index: 4411688 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4154. Min Range: -7.4154
Max Act: 7.0092. Min Act: -0.1700
Data Index: 4545459 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4154. Min Range: -7.4154
Max Act: 7.0092. Min Act: -0.1700
Data Index: 4984053 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4154. Min Range: -7.4154
Max Act: 7.0092. Min Act: -0.1700
Data Index: 5427314 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4154. Min Range: -7.4154
Max Act: 7.0092. Min Act: -0.1700
Data Index: 5033774 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4154. Min Range: -7.4154
Max Act: 6.9779. Min Act: -0.1700
Data Index: 1576023 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4154. Min Range: -7.4154
Max Act: 6.9779. Min Act: -0.1700
Data Index: 100943 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4154. Min Range: -7.4154
Max Act: 6.9779. Min Act: -0.1700
Data Index: 1219360 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4154. Min Range: -7.4154
Max Act: 6.9467. Min Act: -0.1700
Data Index: 8160412 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4154. Min Range: -7.4154
Max Act: 6.9467. Min Act: -0.1700
Data Index: 4627316 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4154. Min Range: -7.4154
Max Act: 6.9154. Min Act: -0.1700
Data Index: 8522710 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4154. Min Range: -7.4154
Max Act: 6.9154. Min Act: -0.1700
Data Index: 8075184 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4154. Min Range: -7.4154
Max Act: 6.8842. Min Act: -0.1700
Data Index: 6458206 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19