Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1762 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.6951. Min Range: -1.6951
Max Act: 1.6951. Min Act: -0.1700
Data Index: 912790 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6951. Min Range: -1.6951
Max Act: 1.6777. Min Act: -0.1689
Data Index: 5741995 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6951. Min Range: -1.6951
Max Act: 1.6429. Min Act: -0.1700
Data Index: 1122185 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6951. Min Range: -1.6951
Max Act: 1.6255. Min Act: -0.1644
Data Index: 4743608 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6951. Min Range: -1.6951
Max Act: 1.6255. Min Act: -0.1700
Data Index: 2222285 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6951. Min Range: -1.6951
Max Act: 1.6255. Min Act: -0.1700
Data Index: 2221326 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6951. Min Range: -1.6951
Max Act: 1.6255. Min Act: -0.1699
Data Index: 2813470 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6951. Min Range: -1.6951
Max Act: 1.6255. Min Act: -0.1700
Data Index: 2897300 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6951. Min Range: -1.6951
Max Act: 1.6255. Min Act: -0.1700
Data Index: 2764972 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6951. Min Range: -1.6951
Max Act: 1.6255. Min Act: -0.1698
Data Index: 2663947 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6951. Min Range: -1.6951
Max Act: 1.6255. Min Act: -0.1700
Data Index: 1546922 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6951. Min Range: -1.6951
Max Act: 1.6255. Min Act: -0.1700
Data Index: 2399493 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6951. Min Range: -1.6951
Max Act: 1.6255. Min Act: -0.1698
Data Index: 1500113 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6951. Min Range: -1.6951
Max Act: 1.6255. Min Act: -0.1700
Data Index: 601769 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6951. Min Range: -1.6951
Max Act: 1.6255. Min Act: -0.1700
Data Index: 1463456 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6951. Min Range: -1.6951
Max Act: 1.6255. Min Act: -0.1700
Data Index: 137616 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6951. Min Range: -1.6951
Max Act: 1.6255. Min Act: -0.1698
Data Index: 1426096 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6951. Min Range: -1.6951
Max Act: 1.6255. Min Act: -0.1699
Data Index: 614202 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6951. Min Range: -1.6951
Max Act: 1.6255. Min Act: -0.1700
Data Index: 258338 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6951. Min Range: -1.6951
Max Act: 1.6255. Min Act: -0.1700
Data Index: 485017 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19