Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 796 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6380. Min Range: -8.6380
Max Act: 8.5755. Min Act: -0.1700
Data Index: 3169595 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6380. Min Range: -8.6380
Max Act: 8.6380. Min Act: -0.1700
Data Index: 2239727 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6380. Min Range: -8.6380
Max Act: 8.3255. Min Act: -0.1700
Data Index: 1469777 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6380. Min Range: -8.6380
Max Act: 8.2630. Min Act: -0.1700
Data Index: 6819315 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6380. Min Range: -8.6380
Max Act: 8.1380. Min Act: -0.1700
Data Index: 6384390 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6380. Min Range: -8.6380
Max Act: 8.1380. Min Act: -0.1700
Data Index: 7365111 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6380. Min Range: -8.6380
Max Act: 8.0130. Min Act: -0.1700
Data Index: 1015401 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6380. Min Range: -8.6380
Max Act: 8.0130. Min Act: -0.1700
Data Index: 4325942 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6380. Min Range: -8.6380
Max Act: 8.0130. Min Act: -0.1700
Data Index: 8328298 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6380. Min Range: -8.6380
Max Act: 8.0130. Min Act: -0.1700
Data Index: 7767548 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6380. Min Range: -8.6380
Max Act: 7.9505. Min Act: -0.1700
Data Index: 8343684 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6380. Min Range: -8.6380
Max Act: 7.9505. Min Act: -0.1700
Data Index: 833200 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6380. Min Range: -8.6380
Max Act: 7.9505. Min Act: -0.1700
Data Index: 5246040 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6380. Min Range: -8.6380
Max Act: 7.9505. Min Act: -0.1700
Data Index: 563308 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6380. Min Range: -8.6380
Max Act: 7.9505. Min Act: -0.1700
Data Index: 4417508 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6380. Min Range: -8.6380
Max Act: 7.8880. Min Act: -0.1700
Data Index: 8193156 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6380. Min Range: -8.6380
Max Act: 7.8880. Min Act: -0.1700
Data Index: 3514696 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6380. Min Range: -8.6380
Max Act: 7.8880. Min Act: -0.1700
Data Index: 3942440 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6380. Min Range: -8.6380
Max Act: 7.8880. Min Act: -0.1700
Data Index: 4443647 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6380. Min Range: -8.6380
Max Act: 7.9505. Min Act: -0.1700
Data Index: 4326658 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #19