Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2093 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2613. Min Range: -9.2613
Max Act: 9.2613. Min Act: -0.1700
Data Index: 664066 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2613. Min Range: -9.2613
Max Act: 9.0738. Min Act: -0.1700
Data Index: 3882554 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2613. Min Range: -9.2613
Max Act: 9.0738. Min Act: -0.1700
Data Index: 5680083 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2613. Min Range: -9.2613
Max Act: 9.0738. Min Act: -0.1700
Data Index: 3133543 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2613. Min Range: -9.2613
Max Act: 9.0738. Min Act: -0.1700
Data Index: 2099182 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2613. Min Range: -9.2613
Max Act: 8.9488. Min Act: -0.1700
Data Index: 4746037 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2613. Min Range: -9.2613
Max Act: 8.9488. Min Act: -0.1700
Data Index: 5676777 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2613. Min Range: -9.2613
Max Act: 8.9488. Min Act: -0.1700
Data Index: 7256950 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2613. Min Range: -9.2613
Max Act: 8.8863. Min Act: -0.1700
Data Index: 2057598 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2613. Min Range: -9.2613
Max Act: 8.8238. Min Act: -0.1700
Data Index: 1070441 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2613. Min Range: -9.2613
Max Act: 8.8238. Min Act: -0.1700
Data Index: 2580554 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2613. Min Range: -9.2613
Max Act: 8.8238. Min Act: -0.1700
Data Index: 6203007 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2613. Min Range: -9.2613
Max Act: 8.8238. Min Act: -0.1700
Data Index: 8624295 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2613. Min Range: -9.2613
Max Act: 8.8238. Min Act: -0.1700
Data Index: 4380220 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2613. Min Range: -9.2613
Max Act: 8.7613. Min Act: -0.1700
Data Index: 8612291 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2613. Min Range: -9.2613
Max Act: 8.7613. Min Act: -0.1700
Data Index: 6579064 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2613. Min Range: -9.2613
Max Act: 8.7613. Min Act: -0.1700
Data Index: 4939676 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2613. Min Range: -9.2613
Max Act: 8.8238. Min Act: -0.1700
Data Index: 7403507 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2613. Min Range: -9.2613
Max Act: 8.6988. Min Act: -0.1700
Data Index: 3095107 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2613. Min Range: -9.2613
Max Act: 8.6988. Min Act: -0.1700
Data Index: 1465854 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19