Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3425 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0361. Min Range: -6.0361
Max Act: 6.0361. Min Act: -0.1700
Data Index: 4868797 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0361. Min Range: -6.0361
Max Act: 5.8799. Min Act: -0.1700
Data Index: 7494456 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0361. Min Range: -6.0361
Max Act: 5.8486. Min Act: -0.1700
Data Index: 2535633 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0361. Min Range: -6.0361
Max Act: 5.8174. Min Act: -0.1700
Data Index: 1920181 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0361. Min Range: -6.0361
Max Act: 5.8174. Min Act: -0.1700
Data Index: 2909560 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0361. Min Range: -6.0361
Max Act: 5.7236. Min Act: -0.1700
Data Index: 4936077 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0361. Min Range: -6.0361
Max Act: 5.7549. Min Act: -0.1700
Data Index: 2916402 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0361. Min Range: -6.0361
Max Act: 5.7236. Min Act: -0.1700
Data Index: 6871426 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0361. Min Range: -6.0361
Max Act: 5.7861. Min Act: -0.1700
Data Index: 340340 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0361. Min Range: -6.0361
Max Act: 5.7236. Min Act: -0.1700
Data Index: 6368027 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0361. Min Range: -6.0361
Max Act: 5.7236. Min Act: -0.1700
Data Index: 8034956 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0361. Min Range: -6.0361
Max Act: 5.6924. Min Act: -0.1700
Data Index: 8708568 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0361. Min Range: -6.0361
Max Act: 5.7236. Min Act: -0.1700
Data Index: 7455992 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0361. Min Range: -6.0361
Max Act: 5.6924. Min Act: -0.1700
Data Index: 6297250 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0361. Min Range: -6.0361
Max Act: 5.6611. Min Act: -0.1700
Data Index: 797087 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0361. Min Range: -6.0361
Max Act: 5.6611. Min Act: -0.1700
Data Index: 2098995 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0361. Min Range: -6.0361
Max Act: 5.6611. Min Act: -0.1700
Data Index: 8324662 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0361. Min Range: -6.0361
Max Act: 5.6611. Min Act: -0.1700
Data Index: 8414147 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0361. Min Range: -6.0361
Max Act: 5.6611. Min Act: -0.1700
Data Index: 3052191 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0361. Min Range: -6.0361
Max Act: 5.6611. Min Act: -0.1700
Data Index: 871745 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #19