Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2449 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9276. Min Range: -8.9276
Max Act: 8.9276. Min Act: -0.1700
Data Index: 3633827 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9276. Min Range: -8.9276
Max Act: 8.8651. Min Act: -0.1700
Data Index: 902532 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9276. Min Range: -8.9276
Max Act: 8.8651. Min Act: -0.1700
Data Index: 3167844 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9276. Min Range: -8.9276
Max Act: 8.8026. Min Act: -0.1700
Data Index: 3201212 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9276. Min Range: -8.9276
Max Act: 8.8026. Min Act: -0.1700
Data Index: 8700027 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9276. Min Range: -8.9276
Max Act: 8.8026. Min Act: -0.1700
Data Index: 5529395 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9276. Min Range: -8.9276
Max Act: 8.7401. Min Act: -0.1700
Data Index: 2729834 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9276. Min Range: -8.9276
Max Act: 8.6151. Min Act: -0.1700
Data Index: 5325367 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9276. Min Range: -8.9276
Max Act: 8.6151. Min Act: -0.1700
Data Index: 1461092 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9276. Min Range: -8.9276
Max Act: 8.6151. Min Act: -0.1700
Data Index: 6884261 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9276. Min Range: -8.9276
Max Act: 8.5526. Min Act: -0.1700
Data Index: 597091 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9276. Min Range: -8.9276
Max Act: 8.5526. Min Act: -0.1700
Data Index: 1542614 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9276. Min Range: -8.9276
Max Act: 8.4901. Min Act: -0.1700
Data Index: 4070048 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9276. Min Range: -8.9276
Max Act: 8.5526. Min Act: -0.1700
Data Index: 7958801 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9276. Min Range: -8.9276
Max Act: 8.4901. Min Act: -0.1700
Data Index: 1980370 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9276. Min Range: -8.9276
Max Act: 8.4276. Min Act: -0.1700
Data Index: 3781356 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9276. Min Range: -8.9276
Max Act: 8.4276. Min Act: -0.1700
Data Index: 3374420 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9276. Min Range: -8.9276
Max Act: 8.4276. Min Act: -0.1700
Data Index: 7786107 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9276. Min Range: -8.9276
Max Act: 8.4276. Min Act: -0.1700
Data Index: 843137 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9276. Min Range: -8.9276
Max Act: 8.3651. Min Act: -0.1700
Data Index: 7864566 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19