Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1677 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0312. Min Range: -6.0312
Max Act: 6.0312. Min Act: -0.1700
Data Index: 5787608 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0312. Min Range: -6.0312
Max Act: 6.0312. Min Act: -0.1700
Data Index: 5689753 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0312. Min Range: -6.0312
Max Act: 5.8749. Min Act: -0.1700
Data Index: 1064335 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0312. Min Range: -6.0312
Max Act: 5.7187. Min Act: -0.1700
Data Index: 6124058 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0312. Min Range: -6.0312
Max Act: 5.6562. Min Act: -0.1700
Data Index: 661082 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0312. Min Range: -6.0312
Max Act: 5.6249. Min Act: -0.1700
Data Index: 2578679 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0312. Min Range: -6.0312
Max Act: 5.5937. Min Act: -0.1700
Data Index: 8571790 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0312. Min Range: -6.0312
Max Act: 5.5937. Min Act: -0.1700
Data Index: 5980849 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0312. Min Range: -6.0312
Max Act: 5.5937. Min Act: -0.1700
Data Index: 3513054 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0312. Min Range: -6.0312
Max Act: 5.5937. Min Act: -0.1700
Data Index: 2883382 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0312. Min Range: -6.0312
Max Act: 5.4999. Min Act: -0.1700
Data Index: 8390052 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0312. Min Range: -6.0312
Max Act: 5.5312. Min Act: -0.1700
Data Index: 2143174 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0312. Min Range: -6.0312
Max Act: 5.5312. Min Act: -0.1700
Data Index: 4172213 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0312. Min Range: -6.0312
Max Act: 5.5312. Min Act: -0.1700
Data Index: 2214832 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0312. Min Range: -6.0312
Max Act: 5.4999. Min Act: -0.1700
Data Index: 5185204 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0312. Min Range: -6.0312
Max Act: 5.4999. Min Act: -0.1700
Data Index: 2904786 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0312. Min Range: -6.0312
Max Act: 5.4999. Min Act: -0.1700
Data Index: 5787606 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0312. Min Range: -6.0312
Max Act: 5.4999. Min Act: -0.1700
Data Index: 3822900 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0312. Min Range: -6.0312
Max Act: 5.4999. Min Act: -0.1700
Data Index: 7442 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0312. Min Range: -6.0312
Max Act: 5.5312. Min Act: -0.1700
Data Index: 4268144 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19