Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2595 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8175. Min Range: -6.8175
Max Act: 6.8175. Min Act: -0.1700
Data Index: 7407176 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8175. Min Range: -6.8175
Max Act: 6.6925. Min Act: -0.1700
Data Index: 5392859 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8175. Min Range: -6.8175
Max Act: 6.6300. Min Act: -0.1700
Data Index: 8747632 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8175. Min Range: -6.8175
Max Act: 6.3800. Min Act: -0.1700
Data Index: 4263415 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8175. Min Range: -6.8175
Max Act: 6.3488. Min Act: -0.1700
Data Index: 7385383 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8175. Min Range: -6.8175
Max Act: 6.3488. Min Act: -0.1700
Data Index: 3366476 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8175. Min Range: -6.8175
Max Act: 6.2863. Min Act: -0.1700
Data Index: 2855560 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8175. Min Range: -6.8175
Max Act: 6.2238. Min Act: -0.1700
Data Index: 2041595 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8175. Min Range: -6.8175
Max Act: 6.2238. Min Act: -0.1700
Data Index: 8098373 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8175. Min Range: -6.8175
Max Act: 6.1613. Min Act: -0.1700
Data Index: 1937937 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8175. Min Range: -6.8175
Max Act: 6.1613. Min Act: -0.1700
Data Index: 377874 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8175. Min Range: -6.8175
Max Act: 6.1300. Min Act: -0.1700
Data Index: 284136 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8175. Min Range: -6.8175
Max Act: 6.1300. Min Act: -0.1700
Data Index: 1315276 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8175. Min Range: -6.8175
Max Act: 6.1300. Min Act: -0.1700
Data Index: 6049184 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8175. Min Range: -6.8175
Max Act: 6.0988. Min Act: -0.1700
Data Index: 4673329 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8175. Min Range: -6.8175
Max Act: 6.0988. Min Act: -0.1700
Data Index: 4463090 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8175. Min Range: -6.8175
Max Act: 6.0988. Min Act: -0.1700
Data Index: 6364941 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8175. Min Range: -6.8175
Max Act: 6.0675. Min Act: -0.1700
Data Index: 3908098 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8175. Min Range: -6.8175
Max Act: 6.0675. Min Act: -0.1700
Data Index: 6915950 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8175. Min Range: -6.8175
Max Act: 6.0675. Min Act: -0.1700
Data Index: 8454760 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #19