Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3495 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4538. Min Range: -9.4538
Max Act: 9.4538. Min Act: -0.1700
Data Index: 318167 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4538. Min Range: -9.4538
Max Act: 8.9538. Min Act: -0.1700
Data Index: 5028827 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4538. Min Range: -9.4538
Max Act: 9.0163. Min Act: -0.1700
Data Index: 893102 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4538. Min Range: -9.4538
Max Act: 9.0163. Min Act: -0.1700
Data Index: 867182 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4538. Min Range: -9.4538
Max Act: 8.9538. Min Act: -0.1700
Data Index: 2339501 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4538. Min Range: -9.4538
Max Act: 8.9538. Min Act: -0.1700
Data Index: 78392 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4538. Min Range: -9.4538
Max Act: 8.9538. Min Act: -0.1700
Data Index: 2736456 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4538. Min Range: -9.4538
Max Act: 8.8913. Min Act: -0.1700
Data Index: 6191391 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4538. Min Range: -9.4538
Max Act: 8.8913. Min Act: -0.1700
Data Index: 867195 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4538. Min Range: -9.4538
Max Act: 8.8288. Min Act: -0.1700
Data Index: 5820975 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4538. Min Range: -9.4538
Max Act: 8.8288. Min Act: -0.1700
Data Index: 1090024 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4538. Min Range: -9.4538
Max Act: 8.8288. Min Act: -0.1700
Data Index: 2868299 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4538. Min Range: -9.4538
Max Act: 8.8288. Min Act: -0.1700
Data Index: 1328728 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4538. Min Range: -9.4538
Max Act: 8.8288. Min Act: -0.1700
Data Index: 6812967 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4538. Min Range: -9.4538
Max Act: 8.7663. Min Act: -0.1700
Data Index: 2270495 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4538. Min Range: -9.4538
Max Act: 8.8288. Min Act: -0.1700
Data Index: 513859 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4538. Min Range: -9.4538
Max Act: 8.8288. Min Act: -0.1700
Data Index: 604695 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4538. Min Range: -9.4538
Max Act: 8.7663. Min Act: -0.1700
Data Index: 5825280 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4538. Min Range: -9.4538
Max Act: 8.7663. Min Act: -0.1700
Data Index: 1449345 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4538. Min Range: -9.4538
Max Act: 8.8288. Min Act: -0.1700
Data Index: 1025884 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19