Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1143 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3970. Min Range: -8.3970
Max Act: 8.3970. Min Act: -0.1700
Data Index: 7899537 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3970. Min Range: -8.3970
Max Act: 8.3032. Min Act: -0.1700
Data Index: 169135 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3970. Min Range: -8.3970
Max Act: 8.3345. Min Act: -0.1700
Data Index: 4605884 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3970. Min Range: -8.3970
Max Act: 8.2407. Min Act: -0.1700
Data Index: 258145 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3970. Min Range: -8.3970
Max Act: 8.2407. Min Act: -0.1700
Data Index: 3797599 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3970. Min Range: -8.3970
Max Act: 8.2095. Min Act: -0.1700
Data Index: 1466182 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3970. Min Range: -8.3970
Max Act: 8.1782. Min Act: -0.1700
Data Index: 1023323 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3970. Min Range: -8.3970
Max Act: 8.1782. Min Act: -0.1700
Data Index: 2481669 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3970. Min Range: -8.3970
Max Act: 8.1470. Min Act: -0.1700
Data Index: 1253155 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3970. Min Range: -8.3970
Max Act: 8.1470. Min Act: -0.1700
Data Index: 3797601 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3970. Min Range: -8.3970
Max Act: 8.0845. Min Act: -0.1700
Data Index: 1655696 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3970. Min Range: -8.3970
Max Act: 8.0845. Min Act: -0.1700
Data Index: 8270981 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3970. Min Range: -8.3970
Max Act: 7.9907. Min Act: -0.1700
Data Index: 3135567 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3970. Min Range: -8.3970
Max Act: 7.9907. Min Act: -0.1700
Data Index: 267701 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3970. Min Range: -8.3970
Max Act: 7.9907. Min Act: -0.1700
Data Index: 3103512 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3970. Min Range: -8.3970
Max Act: 7.9595. Min Act: -0.1700
Data Index: 531601 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3970. Min Range: -8.3970
Max Act: 7.9282. Min Act: -0.1700
Data Index: 585343 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3970. Min Range: -8.3970
Max Act: 7.9282. Min Act: -0.1700
Data Index: 2981893 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3970. Min Range: -8.3970
Max Act: 7.8970. Min Act: -0.1700
Data Index: 2003537 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3970. Min Range: -8.3970
Max Act: 7.8970. Min Act: -0.1700
Data Index: 2268030 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19