Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2974 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.9792. Min Act: -0.1700
Data Index: 4230353 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.9480. Min Act: -0.1700
Data Index: 5566370 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.9167. Min Act: -0.1700
Data Index: 5350686 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.8542. Min Act: -0.1700
Data Index: 6512556 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.8386. Min Act: -0.1700
Data Index: 4146377 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.8386. Min Act: -0.1700
Data Index: 5766827 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.8073. Min Act: -0.1700
Data Index: 1021743 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.8229. Min Act: -0.1700
Data Index: 5702259 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.7916. Min Act: -0.1700
Data Index: 7824409 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.8073. Min Act: -0.1700
Data Index: 1178759 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.7916. Min Act: -0.1700
Data Index: 4259748 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.7916. Min Act: -0.1700
Data Index: 171748 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.7604. Min Act: -0.1700
Data Index: 1378531 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.7916. Min Act: -0.1700
Data Index: 1436552 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.7604. Min Act: -0.1700
Data Index: 6690976 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.7447. Min Act: -0.1700
Data Index: 3875783 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.7447. Min Act: -0.1700
Data Index: 742157 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.7134. Min Act: -0.1700
Data Index: 632371 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.7134. Min Act: -0.1700
Data Index: 6007151 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9792. Min Range: -3.9792
Max Act: 3.7134. Min Act: -0.1700
Data Index: 3206872 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19