Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2167 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1706. Min Range: -7.1706
Max Act: 7.1706. Min Act: -0.1700
Data Index: 8820265 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1706. Min Range: -7.1706
Max Act: 7.1706. Min Act: -0.1700
Data Index: 7255062 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1706. Min Range: -7.1706
Max Act: 7.0456. Min Act: -0.1700
Data Index: 1745728 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1706. Min Range: -7.1706
Max Act: 7.0144. Min Act: -0.1700
Data Index: 4751682 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1706. Min Range: -7.1706
Max Act: 7.0144. Min Act: -0.1700
Data Index: 1979964 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1706. Min Range: -7.1706
Max Act: 6.9831. Min Act: -0.1700
Data Index: 5336146 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1706. Min Range: -7.1706
Max Act: 6.9519. Min Act: -0.1700
Data Index: 7991593 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1706. Min Range: -7.1706
Max Act: 6.9206. Min Act: -0.1700
Data Index: 4097212 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1706. Min Range: -7.1706
Max Act: 6.9206. Min Act: -0.1700
Data Index: 5016882 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1706. Min Range: -7.1706
Max Act: 6.8894. Min Act: -0.1700
Data Index: 5176511 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1706. Min Range: -7.1706
Max Act: 6.8894. Min Act: -0.1700
Data Index: 3214594 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1706. Min Range: -7.1706
Max Act: 6.8894. Min Act: -0.1700
Data Index: 3963880 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1706. Min Range: -7.1706
Max Act: 6.8581. Min Act: -0.1700
Data Index: 8193806 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1706. Min Range: -7.1706
Max Act: 6.8581. Min Act: -0.1700
Data Index: 8818586 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1706. Min Range: -7.1706
Max Act: 6.7956. Min Act: -0.1700
Data Index: 1444711 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1706. Min Range: -7.1706
Max Act: 6.8269. Min Act: -0.1700
Data Index: 3259242 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1706. Min Range: -7.1706
Max Act: 6.8269. Min Act: -0.1700
Data Index: 5441546 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1706. Min Range: -7.1706
Max Act: 6.7956. Min Act: -0.1700
Data Index: 4991156 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1706. Min Range: -7.1706
Max Act: 6.7956. Min Act: -0.1700
Data Index: 4962892 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1706. Min Range: -7.1706
Max Act: 6.7956. Min Act: -0.1700
Data Index: 650454 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19