Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2644 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5937. Min Range: -9.5937
Max Act: 9.5937. Min Act: -0.1700
Data Index: 5847523 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5937. Min Range: -9.5937
Max Act: 9.2187. Min Act: -0.1700
Data Index: 8327208 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5937. Min Range: -9.5937
Max Act: 9.1562. Min Act: -0.1700
Data Index: 7708360 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5937. Min Range: -9.5937
Max Act: 9.2187. Min Act: -0.1700
Data Index: 6592150 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5937. Min Range: -9.5937
Max Act: 9.0937. Min Act: -0.1700
Data Index: 4012139 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5937. Min Range: -9.5937
Max Act: 8.9687. Min Act: -0.1700
Data Index: 4636662 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5937. Min Range: -9.5937
Max Act: 8.9687. Min Act: -0.1700
Data Index: 6830058 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5937. Min Range: -9.5937
Max Act: 8.8437. Min Act: -0.1700
Data Index: 5695424 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5937. Min Range: -9.5937
Max Act: 8.7812. Min Act: -0.1700
Data Index: 905071 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5937. Min Range: -9.5937
Max Act: 8.7812. Min Act: -0.1700
Data Index: 5203657 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5937. Min Range: -9.5937
Max Act: 8.7187. Min Act: -0.1700
Data Index: 2687759 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5937. Min Range: -9.5937
Max Act: 8.7187. Min Act: -0.1700
Data Index: 7292202 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5937. Min Range: -9.5937
Max Act: 8.7187. Min Act: -0.1700
Data Index: 841987 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5937. Min Range: -9.5937
Max Act: 8.6562. Min Act: -0.1700
Data Index: 608631 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5937. Min Range: -9.5937
Max Act: 8.6562. Min Act: -0.1700
Data Index: 7357522 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5937. Min Range: -9.5937
Max Act: 8.6562. Min Act: -0.1700
Data Index: 8128898 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5937. Min Range: -9.5937
Max Act: 8.6562. Min Act: -0.1700
Data Index: 4578088 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5937. Min Range: -9.5937
Max Act: 8.6562. Min Act: -0.1700
Data Index: 2801405 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5937. Min Range: -9.5937
Max Act: 8.5937. Min Act: -0.1700
Data Index: 6890381 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5937. Min Range: -9.5937
Max Act: 8.5937. Min Act: -0.1700
Data Index: 7431339 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19