Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3659 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9799. Min Range: -6.9799
Max Act: 6.9799. Min Act: -0.1700
Data Index: 4400491 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9799. Min Range: -6.9799
Max Act: 6.7924. Min Act: -0.1700
Data Index: 8633651 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9799. Min Range: -6.9799
Max Act: 6.6361. Min Act: -0.1700
Data Index: 8159924 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9799. Min Range: -6.9799
Max Act: 6.6361. Min Act: -0.1700
Data Index: 717014 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9799. Min Range: -6.9799
Max Act: 6.6049. Min Act: -0.1700
Data Index: 4724731 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9799. Min Range: -6.9799
Max Act: 6.5736. Min Act: -0.1700
Data Index: 3121773 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9799. Min Range: -6.9799
Max Act: 6.5424. Min Act: -0.1700
Data Index: 3892872 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9799. Min Range: -6.9799
Max Act: 6.5424. Min Act: -0.1700
Data Index: 6694458 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9799. Min Range: -6.9799
Max Act: 6.5424. Min Act: -0.1700
Data Index: 7253110 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9799. Min Range: -6.9799
Max Act: 6.4799. Min Act: -0.1700
Data Index: 5048439 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9799. Min Range: -6.9799
Max Act: 6.4486. Min Act: -0.1700
Data Index: 6761070 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9799. Min Range: -6.9799
Max Act: 6.4486. Min Act: -0.1700
Data Index: 3392680 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9799. Min Range: -6.9799
Max Act: 6.4486. Min Act: -0.1700
Data Index: 2635104 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9799. Min Range: -6.9799
Max Act: 6.3861. Min Act: -0.1700
Data Index: 6467062 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9799. Min Range: -6.9799
Max Act: 6.3861. Min Act: -0.1700
Data Index: 6157285 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9799. Min Range: -6.9799
Max Act: 6.3549. Min Act: -0.1700
Data Index: 4400492 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9799. Min Range: -6.9799
Max Act: 6.3236. Min Act: -0.1700
Data Index: 6393140 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9799. Min Range: -6.9799
Max Act: 6.3236. Min Act: -0.1700
Data Index: 4138941 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9799. Min Range: -6.9799
Max Act: 6.3236. Min Act: -0.1700
Data Index: 6103964 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9799. Min Range: -6.9799
Max Act: 6.3236. Min Act: -0.1700
Data Index: 6213912 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19