Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3562 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5972. Min Range: -5.5972
Max Act: 5.5972. Min Act: -0.1700
Data Index: 35371 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5972. Min Range: -5.5972
Max Act: 5.5347. Min Act: -0.1700
Data Index: 7877340 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5972. Min Range: -5.5972
Max Act: 5.5034. Min Act: -0.1700
Data Index: 5645800 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5972. Min Range: -5.5972
Max Act: 5.5034. Min Act: -0.1700
Data Index: 1701465 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5972. Min Range: -5.5972
Max Act: 5.4722. Min Act: -0.1700
Data Index: 8078237 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5972. Min Range: -5.5972
Max Act: 5.4722. Min Act: -0.1700
Data Index: 3811650 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5972. Min Range: -5.5972
Max Act: 5.4097. Min Act: -0.1700
Data Index: 275175 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5972. Min Range: -5.5972
Max Act: 5.4097. Min Act: -0.1700
Data Index: 7406953 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5972. Min Range: -5.5972
Max Act: 5.3784. Min Act: -0.1700
Data Index: 8078240 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5972. Min Range: -5.5972
Max Act: 5.3159. Min Act: -0.1700
Data Index: 2536883 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5972. Min Range: -5.5972
Max Act: 5.3159. Min Act: -0.1700
Data Index: 2636914 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5972. Min Range: -5.5972
Max Act: 5.3159. Min Act: -0.1700
Data Index: 7010719 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5972. Min Range: -5.5972
Max Act: 5.3159. Min Act: -0.1700
Data Index: 8078238 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5972. Min Range: -5.5972
Max Act: 5.3159. Min Act: -0.1700
Data Index: 881900 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5972. Min Range: -5.5972
Max Act: 5.2534. Min Act: -0.1700
Data Index: 247935 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5972. Min Range: -5.5972
Max Act: 5.3159. Min Act: -0.1700
Data Index: 5124862 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5972. Min Range: -5.5972
Max Act: 5.2847. Min Act: -0.1700
Data Index: 2418893 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5972. Min Range: -5.5972
Max Act: 5.2534. Min Act: -0.1700
Data Index: 7436243 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5972. Min Range: -5.5972
Max Act: 5.2534. Min Act: -0.1700
Data Index: 2418892 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5972. Min Range: -5.5972
Max Act: 5.2534. Min Act: -0.1700
Data Index: 2920565 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #19