Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3143 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1343. Min Range: -7.1343
Max Act: 7.1343. Min Act: -0.1700
Data Index: 2878356 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1343. Min Range: -7.1343
Max Act: 7.0718. Min Act: -0.1700
Data Index: 4366940 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1343. Min Range: -7.1343
Max Act: 6.7280. Min Act: -0.1700
Data Index: 2312010 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1343. Min Range: -7.1343
Max Act: 6.6030. Min Act: -0.1700
Data Index: 4421203 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1343. Min Range: -7.1343
Max Act: 6.6030. Min Act: -0.1700
Data Index: 5777490 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1343. Min Range: -7.1343
Max Act: 6.6343. Min Act: -0.1700
Data Index: 2469917 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1343. Min Range: -7.1343
Max Act: 6.5718. Min Act: -0.1700
Data Index: 5353655 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1343. Min Range: -7.1343
Max Act: 6.5405. Min Act: -0.1700
Data Index: 4122324 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1343. Min Range: -7.1343
Max Act: 6.5718. Min Act: -0.1700
Data Index: 4249897 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1343. Min Range: -7.1343
Max Act: 6.5093. Min Act: -0.1700
Data Index: 7901580 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1343. Min Range: -7.1343
Max Act: 6.5093. Min Act: -0.1700
Data Index: 6297689 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1343. Min Range: -7.1343
Max Act: 6.4780. Min Act: -0.1700
Data Index: 2266190 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1343. Min Range: -7.1343
Max Act: 6.4780. Min Act: -0.1700
Data Index: 3454014 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1343. Min Range: -7.1343
Max Act: 6.4468. Min Act: -0.1700
Data Index: 6945672 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1343. Min Range: -7.1343
Max Act: 6.4468. Min Act: -0.1700
Data Index: 5467144 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1343. Min Range: -7.1343
Max Act: 6.4468. Min Act: -0.1700
Data Index: 8484240 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1343. Min Range: -7.1343
Max Act: 6.4468. Min Act: -0.1700
Data Index: 1477028 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1343. Min Range: -7.1343
Max Act: 6.4468. Min Act: -0.1700
Data Index: 587682 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1343. Min Range: -7.1343
Max Act: 6.4155. Min Act: -0.1700
Data Index: 957628 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1343. Min Range: -7.1343
Max Act: 6.4155. Min Act: -0.1700
Data Index: 2184242 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19