Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6027 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3105. Min Range: -7.3105
Max Act: 7.3105. Min Act: -0.1700
Data Index: 759490 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3105. Min Range: -7.3105
Max Act: 7.2480. Min Act: -0.1700
Data Index: 3238900 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3105. Min Range: -7.3105
Max Act: 7.1855. Min Act: -0.1700
Data Index: 7813307 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3105. Min Range: -7.3105
Max Act: 7.1855. Min Act: -0.1700
Data Index: 487436 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3105. Min Range: -7.3105
Max Act: 7.1855. Min Act: -0.1700
Data Index: 6695598 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3105. Min Range: -7.3105
Max Act: 7.1855. Min Act: -0.1700
Data Index: 6458105 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3105. Min Range: -7.3105
Max Act: 7.1855. Min Act: -0.1700
Data Index: 6433515 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3105. Min Range: -7.3105
Max Act: 7.1855. Min Act: -0.1700
Data Index: 6361245 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3105. Min Range: -7.3105
Max Act: 7.1855. Min Act: -0.1700
Data Index: 6330644 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3105. Min Range: -7.3105
Max Act: 7.1855. Min Act: -0.1700
Data Index: 6267416 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3105. Min Range: -7.3105
Max Act: 7.1855. Min Act: -0.1700
Data Index: 5627030 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3105. Min Range: -7.3105
Max Act: 7.1855. Min Act: -0.1700
Data Index: 4158569 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3105. Min Range: -7.3105
Max Act: 7.1855. Min Act: -0.1699
Data Index: 4025048 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3105. Min Range: -7.3105
Max Act: 7.1855. Min Act: -0.1700
Data Index: 1962 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3105. Min Range: -7.3105
Max Act: 7.1855. Min Act: -0.1700
Data Index: 3960879 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3105. Min Range: -7.3105
Max Act: 7.1855. Min Act: -0.1700
Data Index: 3664176 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3105. Min Range: -7.3105
Max Act: 7.1855. Min Act: -0.1700
Data Index: 3420904 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3105. Min Range: -7.3105
Max Act: 7.1855. Min Act: -0.1700
Data Index: 2935492 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3105. Min Range: -7.3105
Max Act: 7.1855. Min Act: -0.1700
Data Index: 2105263 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3105. Min Range: -7.3105
Max Act: 7.1855. Min Act: -0.1700
Data Index: 1581368 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19