Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3016 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6822. Min Range: -6.6822
Max Act: 6.6822. Min Act: -0.1700
Data Index: 438680 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6822. Min Range: -6.6822
Max Act: 6.6822. Min Act: -0.1700
Data Index: 6461587 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6822. Min Range: -6.6822
Max Act: 6.6510. Min Act: -0.1700
Data Index: 42380 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6822. Min Range: -6.6822
Max Act: 6.6822. Min Act: -0.1700
Data Index: 1733092 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6822. Min Range: -6.6822
Max Act: 6.6510. Min Act: -0.1700
Data Index: 7209321 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6822. Min Range: -6.6822
Max Act: 6.6510. Min Act: -0.1700
Data Index: 2870489 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6822. Min Range: -6.6822
Max Act: 6.5260. Min Act: -0.1700
Data Index: 6010306 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6822. Min Range: -6.6822
Max Act: 6.5260. Min Act: -0.1700
Data Index: 969154 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6822. Min Range: -6.6822
Max Act: 6.4947. Min Act: -0.1700
Data Index: 4509465 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6822. Min Range: -6.6822
Max Act: 6.4635. Min Act: -0.1700
Data Index: 7646617 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6822. Min Range: -6.6822
Max Act: 6.4635. Min Act: -0.1700
Data Index: 1328673 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6822. Min Range: -6.6822
Max Act: 6.4635. Min Act: -0.1700
Data Index: 5988406 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6822. Min Range: -6.6822
Max Act: 6.4635. Min Act: -0.1700
Data Index: 7833142 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6822. Min Range: -6.6822
Max Act: 6.4635. Min Act: -0.1700
Data Index: 4336223 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6822. Min Range: -6.6822
Max Act: 6.4322. Min Act: -0.1700
Data Index: 3217930 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6822. Min Range: -6.6822
Max Act: 6.4635. Min Act: -0.1700
Data Index: 4916594 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6822. Min Range: -6.6822
Max Act: 6.4322. Min Act: -0.1700
Data Index: 4094261 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6822. Min Range: -6.6822
Max Act: 6.4010. Min Act: -0.1700
Data Index: 5385360 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6822. Min Range: -6.6822
Max Act: 6.3697. Min Act: -0.1700
Data Index: 6806942 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6822. Min Range: -6.6822
Max Act: 6.3697. Min Act: -0.1700
Data Index: 5381852 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19