Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4383 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0533. Min Range: -9.0533
Max Act: 9.0533. Min Act: -0.1700
Data Index: 1406291 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0533. Min Range: -9.0533
Max Act: 8.9908. Min Act: -0.1700
Data Index: 1743197 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0533. Min Range: -9.0533
Max Act: 8.7408. Min Act: -0.1700
Data Index: 1077642 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0533. Min Range: -9.0533
Max Act: 8.6158. Min Act: -0.1700
Data Index: 1229182 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0533. Min Range: -9.0533
Max Act: 8.4283. Min Act: -0.1700
Data Index: 2020409 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0533. Min Range: -9.0533
Max Act: 8.3658. Min Act: -0.1700
Data Index: 3485573 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0533. Min Range: -9.0533
Max Act: 8.3658. Min Act: -0.1700
Data Index: 3180502 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0533. Min Range: -9.0533
Max Act: 8.3658. Min Act: -0.1700
Data Index: 1163556 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0533. Min Range: -9.0533
Max Act: 8.3658. Min Act: -0.1700
Data Index: 3837852 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0533. Min Range: -9.0533
Max Act: 8.2408. Min Act: -0.1700
Data Index: 8391709 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0533. Min Range: -9.0533
Max Act: 8.2408. Min Act: -0.1700
Data Index: 3778120 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0533. Min Range: -9.0533
Max Act: 8.2096. Min Act: -0.1700
Data Index: 2710253 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0533. Min Range: -9.0533
Max Act: 8.2408. Min Act: -0.1700
Data Index: 8077353 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0533. Min Range: -9.0533
Max Act: 8.2408. Min Act: -0.1700
Data Index: 4102019 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0533. Min Range: -9.0533
Max Act: 8.2096. Min Act: -0.1700
Data Index: 4765188 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0533. Min Range: -9.0533
Max Act: 8.1158. Min Act: -0.1700
Data Index: 2032333 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0533. Min Range: -9.0533
Max Act: 8.1783. Min Act: -0.1700
Data Index: 6977305 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0533. Min Range: -9.0533
Max Act: 8.1471. Min Act: -0.1700
Data Index: 7194159 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0533. Min Range: -9.0533
Max Act: 8.0533. Min Act: -0.1700
Data Index: 1316654 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0533. Min Range: -9.0533
Max Act: 8.0846. Min Act: -0.1700
Data Index: 169442 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19