Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2961 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1271. Min Range: -7.1271
Max Act: 7.1271. Min Act: -0.1700
Data Index: 2415759 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1271. Min Range: -7.1271
Max Act: 7.0959. Min Act: -0.1700
Data Index: 3690111 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1271. Min Range: -7.1271
Max Act: 7.1271. Min Act: -0.1700
Data Index: 4614351 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1271. Min Range: -7.1271
Max Act: 7.0959. Min Act: -0.1700
Data Index: 1328763 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1271. Min Range: -7.1271
Max Act: 7.0646. Min Act: -0.1700
Data Index: 1440180 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1271. Min Range: -7.1271
Max Act: 7.0646. Min Act: -0.1700
Data Index: 4722396 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1271. Min Range: -7.1271
Max Act: 6.9396. Min Act: -0.1700
Data Index: 8304690 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1271. Min Range: -7.1271
Max Act: 6.9396. Min Act: -0.1700
Data Index: 7044357 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1271. Min Range: -7.1271
Max Act: 6.9084. Min Act: -0.1700
Data Index: 14809 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1271. Min Range: -7.1271
Max Act: 6.9084. Min Act: -0.1700
Data Index: 4918717 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1271. Min Range: -7.1271
Max Act: 6.8771. Min Act: -0.1700
Data Index: 786530 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1271. Min Range: -7.1271
Max Act: 6.8771. Min Act: -0.1700
Data Index: 1914619 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1271. Min Range: -7.1271
Max Act: 6.8459. Min Act: -0.1700
Data Index: 2444169 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1271. Min Range: -7.1271
Max Act: 6.8459. Min Act: -0.1700
Data Index: 3985362 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1271. Min Range: -7.1271
Max Act: 6.7834. Min Act: -0.1700
Data Index: 6467814 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1271. Min Range: -7.1271
Max Act: 6.7834. Min Act: -0.1700
Data Index: 1365885 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1271. Min Range: -7.1271
Max Act: 6.7834. Min Act: -0.1700
Data Index: 6743287 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1271. Min Range: -7.1271
Max Act: 6.7834. Min Act: -0.1700
Data Index: 7875883 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1271. Min Range: -7.1271
Max Act: 6.7834. Min Act: -0.1700
Data Index: 6605658 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1271. Min Range: -7.1271
Max Act: 6.7521. Min Act: -0.1700
Data Index: 8747082 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19