Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4287 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.3963. Min Range: -1.3963
Max Act: 1.3963. Min Act: -0.1700
Data Index: 1375937 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3963. Min Range: -1.3963
Max Act: 1.3258. Min Act: -0.1700
Data Index: 4661603 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3963. Min Range: -1.3963
Max Act: 1.3081. Min Act: -0.1700
Data Index: 2414004 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3963. Min Range: -1.3963
Max Act: 1.3081. Min Act: -0.1700
Data Index: 1024355 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3963. Min Range: -1.3963
Max Act: 1.2729. Min Act: -0.1700
Data Index: 6174383 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3963. Min Range: -1.3963
Max Act: 1.2552. Min Act: -0.1700
Data Index: 5307525 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3963. Min Range: -1.3963
Max Act: 1.2729. Min Act: -0.1700
Data Index: 5145617 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3963. Min Range: -1.3963
Max Act: 1.2905. Min Act: -0.1700
Data Index: 719427 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3963. Min Range: -1.3963
Max Act: 1.2729. Min Act: -0.1700
Data Index: 8456496 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3963. Min Range: -1.3963
Max Act: 1.2729. Min Act: -0.1700
Data Index: 1723331 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3963. Min Range: -1.3963
Max Act: 1.2729. Min Act: -0.1700
Data Index: 4171387 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3963. Min Range: -1.3963
Max Act: 1.2552. Min Act: -0.1700
Data Index: 558710 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3963. Min Range: -1.3963
Max Act: 1.2552. Min Act: -0.1700
Data Index: 2194499 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3963. Min Range: -1.3963
Max Act: 1.2552. Min Act: -0.1700
Data Index: 2015499 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3963. Min Range: -1.3963
Max Act: 1.2552. Min Act: -0.1700
Data Index: 5230989 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3963. Min Range: -1.3963
Max Act: 1.2376. Min Act: -0.1700
Data Index: 558720 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3963. Min Range: -1.3963
Max Act: 1.2376. Min Act: -0.1700
Data Index: 2065235 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3963. Min Range: -1.3963
Max Act: 1.2376. Min Act: -0.1700
Data Index: 337740 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3963. Min Range: -1.3963
Max Act: 1.2376. Min Act: -0.1700
Data Index: 3283804 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3963. Min Range: -1.3963
Max Act: 1.2376. Min Act: -0.1700
Data Index: 5525975 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19