Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4391 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.4615. Min Range: -0.4615
Max Act: 0.4615. Min Act: -0.1700
Data Index: 5297416 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4615. Min Range: -0.4615
Max Act: 0.4541. Min Act: -0.1700
Data Index: 2446813 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4615. Min Range: -0.4615
Max Act: 0.4541. Min Act: -0.1699
Data Index: 4493885 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4615. Min Range: -0.4615
Max Act: 0.4541. Min Act: -0.1700
Data Index: 3829464 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4615. Min Range: -0.4615
Max Act: 0.4396. Min Act: -0.1684
Data Index: 360220 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4615. Min Range: -0.4615
Max Act: 0.4251. Min Act: -0.1690
Data Index: 3560253 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4615. Min Range: -0.4615
Max Act: 0.4323. Min Act: -0.1700
Data Index: 2975391 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4615. Min Range: -0.4615
Max Act: 0.4180. Min Act: -0.1700
Data Index: 8732632 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4615. Min Range: -0.4615
Max Act: 0.4251. Min Act: -0.1700
Data Index: 8271768 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4615. Min Range: -0.4615
Max Act: 0.4180. Min Act: -0.1700
Data Index: 8065306 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4615. Min Range: -0.4615
Max Act: 0.4109. Min Act: -0.1700
Data Index: 5610911 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4615. Min Range: -0.4615
Max Act: 0.4109. Min Act: -0.1700
Data Index: 1907271 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4615. Min Range: -0.4615
Max Act: 0.4180. Min Act: -0.1699
Data Index: 1552747 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4615. Min Range: -0.4615
Max Act: 0.4180. Min Act: -0.1700
Data Index: 3483653 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4615. Min Range: -0.4615
Max Act: 0.4109. Min Act: -0.1700
Data Index: 7979042 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4615. Min Range: -0.4615
Max Act: 0.4038. Min Act: -0.1697
Data Index: 6210226 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4615. Min Range: -0.4615
Max Act: 0.4109. Min Act: -0.1697
Data Index: 8724912 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4615. Min Range: -0.4615
Max Act: 0.4109. Min Act: -0.1696
Data Index: 2863487 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4615. Min Range: -0.4615
Max Act: 0.4038. Min Act: -0.1700
Data Index: 3286503 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4615. Min Range: -0.4615
Max Act: 0.4038. Min Act: -0.1700
Data Index: 4163696 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19