Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3710 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5658. Min Range: -9.5658
Max Act: 9.5658. Min Act: -0.1700
Data Index: 7555147 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5658. Min Range: -9.5658
Max Act: 9.3158. Min Act: -0.1700
Data Index: 2587988 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5658. Min Range: -9.5658
Max Act: 9.1908. Min Act: -0.1700
Data Index: 7003743 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5658. Min Range: -9.5658
Max Act: 9.1908. Min Act: -0.1700
Data Index: 6977054 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5658. Min Range: -9.5658
Max Act: 9.1283. Min Act: -0.1700
Data Index: 6740736 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5658. Min Range: -9.5658
Max Act: 9.1908. Min Act: -0.1700
Data Index: 8589202 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5658. Min Range: -9.5658
Max Act: 9.1283. Min Act: -0.1700
Data Index: 4471575 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5658. Min Range: -9.5658
Max Act: 9.0658. Min Act: -0.1700
Data Index: 8415908 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5658. Min Range: -9.5658
Max Act: 9.0033. Min Act: -0.1700
Data Index: 6623250 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5658. Min Range: -9.5658
Max Act: 9.0033. Min Act: -0.1700
Data Index: 3496236 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5658. Min Range: -9.5658
Max Act: 9.0033. Min Act: -0.1700
Data Index: 4868268 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5658. Min Range: -9.5658
Max Act: 8.9408. Min Act: -0.1700
Data Index: 2088117 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5658. Min Range: -9.5658
Max Act: 8.9408. Min Act: -0.1700
Data Index: 5643868 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5658. Min Range: -9.5658
Max Act: 8.8783. Min Act: -0.1700
Data Index: 8601309 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5658. Min Range: -9.5658
Max Act: 8.8158. Min Act: -0.1700
Data Index: 4138501 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5658. Min Range: -9.5658
Max Act: 8.8783. Min Act: -0.1700
Data Index: 5514512 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5658. Min Range: -9.5658
Max Act: 8.8783. Min Act: -0.1700
Data Index: 5177992 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5658. Min Range: -9.5658
Max Act: 8.8783. Min Act: -0.1700
Data Index: 3519485 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5658. Min Range: -9.5658
Max Act: 8.8158. Min Act: -0.1700
Data Index: 7153198 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5658. Min Range: -9.5658
Max Act: 8.8783. Min Act: -0.1700
Data Index: 6068707 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19