Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4050 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7615. Min Range: -1.7615
Max Act: 1.7615. Min Act: -0.1700
Data Index: 7400890 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7615. Min Range: -1.7615
Max Act: 1.7096. Min Act: -0.1700
Data Index: 5969953 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7615. Min Range: -1.7615
Max Act: 1.7270. Min Act: -0.1700
Data Index: 5987591 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7615. Min Range: -1.7615
Max Act: 1.7096. Min Act: -0.1700
Data Index: 3906062 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7615. Min Range: -1.7615
Max Act: 1.7096. Min Act: -0.1700
Data Index: 5923499 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7615. Min Range: -1.7615
Max Act: 1.7010. Min Act: -0.1700
Data Index: 4819612 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7615. Min Range: -1.7615
Max Act: 1.6836. Min Act: -0.1700
Data Index: 7296457 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7615. Min Range: -1.7615
Max Act: 1.6662. Min Act: -0.1700
Data Index: 1001282 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7615. Min Range: -1.7615
Max Act: 1.6749. Min Act: -0.1700
Data Index: 6572425 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7615. Min Range: -1.7615
Max Act: 1.6749. Min Act: -0.1700
Data Index: 5429938 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7615. Min Range: -1.7615
Max Act: 1.6749. Min Act: -0.1700
Data Index: 4682135 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7615. Min Range: -1.7615
Max Act: 1.6749. Min Act: -0.1700
Data Index: 3781756 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7615. Min Range: -1.7615
Max Act: 1.6749. Min Act: -0.1700
Data Index: 934825 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7615. Min Range: -1.7615
Max Act: 1.6662. Min Act: -0.1700
Data Index: 508224 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7615. Min Range: -1.7615
Max Act: 1.6662. Min Act: -0.1700
Data Index: 5127035 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7615. Min Range: -1.7615
Max Act: 1.6488. Min Act: -0.1700
Data Index: 2193518 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7615. Min Range: -1.7615
Max Act: 1.6488. Min Act: -0.1700
Data Index: 5400063 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7615. Min Range: -1.7615
Max Act: 1.6401. Min Act: -0.1700
Data Index: 124084 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7615. Min Range: -1.7615
Max Act: 1.6488. Min Act: -0.1700
Data Index: 2535787 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7615. Min Range: -1.7615
Max Act: 1.6401. Min Act: -0.1700
Data Index: 7990042 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19