Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1804 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1623. Min Range: -7.1623
Max Act: 7.1623. Min Act: -0.1700
Data Index: 2741782 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1623. Min Range: -7.1623
Max Act: 7.1310. Min Act: -0.1700
Data Index: 8125109 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1623. Min Range: -7.1623
Max Act: 7.0998. Min Act: -0.1700
Data Index: 8405733 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1623. Min Range: -7.1623
Max Act: 7.0998. Min Act: -0.1700
Data Index: 2427408 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1623. Min Range: -7.1623
Max Act: 7.0373. Min Act: -0.1700
Data Index: 4096626 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1623. Min Range: -7.1623
Max Act: 7.0373. Min Act: -0.1700
Data Index: 5557718 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1623. Min Range: -7.1623
Max Act: 7.0373. Min Act: -0.1700
Data Index: 2582976 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1623. Min Range: -7.1623
Max Act: 7.0373. Min Act: -0.1700
Data Index: 348175 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1623. Min Range: -7.1623
Max Act: 7.0060. Min Act: -0.1700
Data Index: 2759182 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1623. Min Range: -7.1623
Max Act: 7.0060. Min Act: -0.1700
Data Index: 282816 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1623. Min Range: -7.1623
Max Act: 7.0060. Min Act: -0.1700
Data Index: 8514338 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1623. Min Range: -7.1623
Max Act: 7.0060. Min Act: -0.1700
Data Index: 8242298 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1623. Min Range: -7.1623
Max Act: 6.9748. Min Act: -0.1700
Data Index: 6629006 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1623. Min Range: -7.1623
Max Act: 6.9748. Min Act: -0.1700
Data Index: 72828 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1623. Min Range: -7.1623
Max Act: 6.9748. Min Act: -0.1700
Data Index: 7401554 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1623. Min Range: -7.1623
Max Act: 6.9748. Min Act: -0.1700
Data Index: 6332040 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1623. Min Range: -7.1623
Max Act: 6.9748. Min Act: -0.1700
Data Index: 1231478 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1623. Min Range: -7.1623
Max Act: 6.9748. Min Act: -0.1700
Data Index: 2901311 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1623. Min Range: -7.1623
Max Act: 6.9748. Min Act: -0.1700
Data Index: 132146 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1623. Min Range: -7.1623
Max Act: 6.9748. Min Act: -0.1700
Data Index: 7556206 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #19