Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3216 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9362. Min Range: -6.9362
Max Act: 6.9362. Min Act: -0.1700
Data Index: 3453424 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9362. Min Range: -6.9362
Max Act: 6.7174. Min Act: -0.1700
Data Index: 7712688 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9362. Min Range: -6.9362
Max Act: 6.6237. Min Act: -0.1700
Data Index: 3897717 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9362. Min Range: -6.9362
Max Act: 6.6549. Min Act: -0.1700
Data Index: 8433919 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9362. Min Range: -6.9362
Max Act: 6.6549. Min Act: -0.1700
Data Index: 4668616 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9362. Min Range: -6.9362
Max Act: 6.5924. Min Act: -0.1700
Data Index: 188778 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9362. Min Range: -6.9362
Max Act: 6.5612. Min Act: -0.1700
Data Index: 4293213 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9362. Min Range: -6.9362
Max Act: 6.4987. Min Act: -0.1700
Data Index: 1062189 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9362. Min Range: -6.9362
Max Act: 6.4674. Min Act: -0.1700
Data Index: 889809 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9362. Min Range: -6.9362
Max Act: 6.4674. Min Act: -0.1700
Data Index: 5191874 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9362. Min Range: -6.9362
Max Act: 6.4674. Min Act: -0.1700
Data Index: 1062190 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9362. Min Range: -6.9362
Max Act: 6.4362. Min Act: -0.1700
Data Index: 8350984 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9362. Min Range: -6.9362
Max Act: 6.4362. Min Act: -0.1700
Data Index: 6106530 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9362. Min Range: -6.9362
Max Act: 6.4362. Min Act: -0.1700
Data Index: 617274 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9362. Min Range: -6.9362
Max Act: 6.4049. Min Act: -0.1700
Data Index: 553153 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9362. Min Range: -6.9362
Max Act: 6.4049. Min Act: -0.1700
Data Index: 1892971 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9362. Min Range: -6.9362
Max Act: 6.4049. Min Act: -0.1700
Data Index: 8192151 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9362. Min Range: -6.9362
Max Act: 6.4049. Min Act: -0.1700
Data Index: 93205 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9362. Min Range: -6.9362
Max Act: 6.4049. Min Act: -0.1700
Data Index: 5370991 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9362. Min Range: -6.9362
Max Act: 6.4049. Min Act: -0.1700
Data Index: 6543454 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #19