Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4754 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3081. Min Range: -8.3081
Max Act: 8.3081. Min Act: -0.1700
Data Index: 8137613 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3081. Min Range: -8.3081
Max Act: 8.1831. Min Act: -0.1700
Data Index: 5997065 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3081. Min Range: -8.3081
Max Act: 8.1206. Min Act: -0.1700
Data Index: 4574674 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3081. Min Range: -8.3081
Max Act: 8.1206. Min Act: -0.1700
Data Index: 6973883 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3081. Min Range: -8.3081
Max Act: 8.1206. Min Act: -0.1700
Data Index: 6333243 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3081. Min Range: -8.3081
Max Act: 8.0581. Min Act: -0.1700
Data Index: 3055376 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3081. Min Range: -8.3081
Max Act: 8.0581. Min Act: -0.1700
Data Index: 6272996 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3081. Min Range: -8.3081
Max Act: 8.0581. Min Act: -0.1700
Data Index: 4773859 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3081. Min Range: -8.3081
Max Act: 7.9956. Min Act: -0.1700
Data Index: 3046838 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3081. Min Range: -8.3081
Max Act: 7.9331. Min Act: -0.1700
Data Index: 1369121 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3081. Min Range: -8.3081
Max Act: 7.9331. Min Act: -0.1700
Data Index: 53767 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3081. Min Range: -8.3081
Max Act: 7.9331. Min Act: -0.1700
Data Index: 8757066 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3081. Min Range: -8.3081
Max Act: 7.8706. Min Act: -0.1700
Data Index: 486131 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3081. Min Range: -8.3081
Max Act: 7.8081. Min Act: -0.1700
Data Index: 3018703 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3081. Min Range: -8.3081
Max Act: 7.8081. Min Act: -0.1700
Data Index: 486137 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3081. Min Range: -8.3081
Max Act: 7.7769. Min Act: -0.1700
Data Index: 4473981 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3081. Min Range: -8.3081
Max Act: 7.7769. Min Act: -0.1700
Data Index: 3183126 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3081. Min Range: -8.3081
Max Act: 7.7456. Min Act: -0.1700
Data Index: 6962568 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3081. Min Range: -8.3081
Max Act: 7.7456. Min Act: -0.1700
Data Index: 3918894 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3081. Min Range: -8.3081
Max Act: 7.7144. Min Act: -0.1700
Data Index: 6711757 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19