Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3930 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.9029. Min Act: -0.1700
Data Index: 7520689 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.8716. Min Act: -0.1700
Data Index: 1433220 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.8091. Min Act: -0.1700
Data Index: 6643599 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.8091. Min Act: -0.1700
Data Index: 7804669 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.8091. Min Act: -0.1700
Data Index: 5451172 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.7466. Min Act: -0.1700
Data Index: 8279916 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.7466. Min Act: -0.1700
Data Index: 3565146 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.7154. Min Act: -0.1700
Data Index: 5524478 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.7154. Min Act: -0.1700
Data Index: 880175 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.7154. Min Act: -0.1700
Data Index: 5850069 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.7154. Min Act: -0.1700
Data Index: 505689 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.6841. Min Act: -0.1700
Data Index: 4910396 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.6841. Min Act: -0.1698
Data Index: 7616693 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.6529. Min Act: -0.1700
Data Index: 1883762 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.6841. Min Act: -0.1700
Data Index: 4104293 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.6841. Min Act: -0.1700
Data Index: 2988986 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.6841. Min Act: -0.1700
Data Index: 3301773 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.6841. Min Act: -0.1700
Data Index: 1978090 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.6529. Min Act: -0.1700
Data Index: 5777544 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9029. Min Range: -4.9029
Max Act: 4.6529. Min Act: -0.1700
Data Index: 990392 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19