Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2717 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4615. Min Range: -6.4615
Max Act: 6.4615. Min Act: -0.1700
Data Index: 2654428 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4615. Min Range: -6.4615
Max Act: 5.9302. Min Act: -0.1700
Data Index: 8215582 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4615. Min Range: -6.4615
Max Act: 5.8677. Min Act: -0.1700
Data Index: 3279958 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4615. Min Range: -6.4615
Max Act: 5.8677. Min Act: -0.1700
Data Index: 3915211 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4615. Min Range: -6.4615
Max Act: 5.7115. Min Act: -0.1700
Data Index: 4704939 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4615. Min Range: -6.4615
Max Act: 5.7427. Min Act: -0.1700
Data Index: 8306078 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4615. Min Range: -6.4615
Max Act: 5.6802. Min Act: -0.1700
Data Index: 7896128 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4615. Min Range: -6.4615
Max Act: 5.6490. Min Act: -0.1700
Data Index: 3574641 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4615. Min Range: -6.4615
Max Act: 5.6177. Min Act: -0.1700
Data Index: 6590859 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4615. Min Range: -6.4615
Max Act: 5.5865. Min Act: -0.1700
Data Index: 3874037 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4615. Min Range: -6.4615
Max Act: 5.5240. Min Act: -0.1700
Data Index: 2160637 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4615. Min Range: -6.4615
Max Act: 5.5240. Min Act: -0.1700
Data Index: 6634158 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4615. Min Range: -6.4615
Max Act: 5.4927. Min Act: -0.1700
Data Index: 1548275 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4615. Min Range: -6.4615
Max Act: 5.4927. Min Act: -0.1700
Data Index: 2649775 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4615. Min Range: -6.4615
Max Act: 5.4927. Min Act: -0.1700
Data Index: 2097177 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4615. Min Range: -6.4615
Max Act: 5.4927. Min Act: -0.1700
Data Index: 3682343 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4615. Min Range: -6.4615
Max Act: 5.4615. Min Act: -0.1700
Data Index: 121860 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4615. Min Range: -6.4615
Max Act: 5.4302. Min Act: -0.1700
Data Index: 789161 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4615. Min Range: -6.4615
Max Act: 5.4302. Min Act: -0.1700
Data Index: 1436637 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4615. Min Range: -6.4615
Max Act: 5.4615. Min Act: -0.1700
Data Index: 5674276 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19