Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2854 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8442. Min Range: -3.8442
Max Act: 3.8442. Min Act: -0.1700
Data Index: 487559 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8442. Min Range: -3.8442
Max Act: 3.6878. Min Act: -0.1700
Data Index: 7447029 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8442. Min Range: -3.8442
Max Act: 3.6722. Min Act: -0.1700
Data Index: 290018 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8442. Min Range: -3.8442
Max Act: 3.6565. Min Act: -0.1700
Data Index: 3233433 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8442. Min Range: -3.8442
Max Act: 3.6096. Min Act: -0.1700
Data Index: 8544120 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8442. Min Range: -3.8442
Max Act: 3.5783. Min Act: -0.1700
Data Index: 2316083 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8442. Min Range: -3.8442
Max Act: 3.5939. Min Act: -0.1700
Data Index: 5205939 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8442. Min Range: -3.8442
Max Act: 3.5783. Min Act: -0.1700
Data Index: 4134847 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8442. Min Range: -3.8442
Max Act: 3.5783. Min Act: -0.1700
Data Index: 2776631 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8442. Min Range: -3.8442
Max Act: 3.5626. Min Act: -0.1700
Data Index: 8606515 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8442. Min Range: -3.8442
Max Act: 3.5470. Min Act: -0.1700
Data Index: 2098359 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8442. Min Range: -3.8442
Max Act: 3.5313. Min Act: -0.1700
Data Index: 8480212 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8442. Min Range: -3.8442
Max Act: 3.5470. Min Act: -0.1700
Data Index: 1015984 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8442. Min Range: -3.8442
Max Act: 3.5313. Min Act: -0.1700
Data Index: 8449382 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8442. Min Range: -3.8442
Max Act: 3.5157. Min Act: -0.1700
Data Index: 6449009 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8442. Min Range: -3.8442
Max Act: 3.5313. Min Act: -0.1700
Data Index: 5892233 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8442. Min Range: -3.8442
Max Act: 3.5313. Min Act: -0.1700
Data Index: 5065679 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8442. Min Range: -3.8442
Max Act: 3.5000. Min Act: -0.1700
Data Index: 4359315 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8442. Min Range: -3.8442
Max Act: 3.5000. Min Act: -0.1700
Data Index: 1633541 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8442. Min Range: -3.8442
Max Act: 3.5000. Min Act: -0.1700
Data Index: 7696793 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19