Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4821 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2211. Min Range: -10.2211
Max Act: 10.2211. Min Act: -0.1700
Data Index: 2075839 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2211. Min Range: -10.2211
Max Act: 10.0336. Min Act: -0.1700
Data Index: 7475894 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2211. Min Range: -10.2211
Max Act: 10.0336. Min Act: -0.1700
Data Index: 7762111 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2211. Min Range: -10.2211
Max Act: 9.9711. Min Act: -0.1700
Data Index: 5941140 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2211. Min Range: -10.2211
Max Act: 9.9086. Min Act: -0.1700
Data Index: 7689517 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2211. Min Range: -10.2211
Max Act: 9.8461. Min Act: -0.1700
Data Index: 552802 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2211. Min Range: -10.2211
Max Act: 9.8461. Min Act: -0.1700
Data Index: 661902 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2211. Min Range: -10.2211
Max Act: 9.7211. Min Act: -0.1700
Data Index: 5652387 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2211. Min Range: -10.2211
Max Act: 9.6586. Min Act: -0.1700
Data Index: 5057641 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2211. Min Range: -10.2211
Max Act: 9.7836. Min Act: -0.1700
Data Index: 2462316 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2211. Min Range: -10.2211
Max Act: 9.6586. Min Act: -0.1700
Data Index: 6552974 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2211. Min Range: -10.2211
Max Act: 9.6586. Min Act: -0.1700
Data Index: 6253786 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2211. Min Range: -10.2211
Max Act: 9.6586. Min Act: -0.1700
Data Index: 6988948 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2211. Min Range: -10.2211
Max Act: 9.5336. Min Act: -0.1700
Data Index: 742561 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2211. Min Range: -10.2211
Max Act: 9.4711. Min Act: -0.1700
Data Index: 2294492 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2211. Min Range: -10.2211
Max Act: 9.4711. Min Act: -0.1700
Data Index: 5375878 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2211. Min Range: -10.2211
Max Act: 9.4086. Min Act: -0.1700
Data Index: 8086967 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2211. Min Range: -10.2211
Max Act: 9.4711. Min Act: -0.1700
Data Index: 4056099 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2211. Min Range: -10.2211
Max Act: 9.4711. Min Act: -0.1700
Data Index: 1302406 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2211. Min Range: -10.2211
Max Act: 9.4086. Min Act: -0.1700
Data Index: 5930647 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #19