Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1380 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8664. Min Range: -2.8664
Max Act: 2.8664. Min Act: -0.1700
Data Index: 7110436 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8664. Min Range: -2.8664
Max Act: 2.7868. Min Act: -0.1700
Data Index: 1720134 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8664. Min Range: -2.8664
Max Act: 2.7550. Min Act: -0.1700
Data Index: 4398363 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8664. Min Range: -2.8664
Max Act: 2.7868. Min Act: -0.1700
Data Index: 7044856 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8664. Min Range: -2.8664
Max Act: 2.7709. Min Act: -0.1700
Data Index: 1755294 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8664. Min Range: -2.8664
Max Act: 2.7868. Min Act: -0.1700
Data Index: 6478014 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8664. Min Range: -2.8664
Max Act: 2.7230. Min Act: -0.1700
Data Index: 5477750 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8664. Min Range: -2.8664
Max Act: 2.7230. Min Act: -0.1700
Data Index: 3633111 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8664. Min Range: -2.8664
Max Act: 2.7230. Min Act: -0.1700
Data Index: 2146096 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8664. Min Range: -2.8664
Max Act: 2.6750. Min Act: -0.1700
Data Index: 1915515 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8664. Min Range: -2.8664
Max Act: 2.6750. Min Act: -0.1700
Data Index: 2309467 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8664. Min Range: -2.8664
Max Act: 2.6750. Min Act: -0.1700
Data Index: 1136994 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8664. Min Range: -2.8664
Max Act: 2.6750. Min Act: -0.1700
Data Index: 4491587 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8664. Min Range: -2.8664
Max Act: 2.6750. Min Act: -0.1700
Data Index: 7539516 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8664. Min Range: -2.8664
Max Act: 2.6590. Min Act: -0.1700
Data Index: 1310394 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8664. Min Range: -2.8664
Max Act: 2.6429. Min Act: -0.1700
Data Index: 568907 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8664. Min Range: -2.8664
Max Act: 2.6590. Min Act: -0.1700
Data Index: 3877769 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8664. Min Range: -2.8664
Max Act: 2.6590. Min Act: -0.1700
Data Index: 1590340 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8664. Min Range: -2.8664
Max Act: 2.6269. Min Act: -0.1700
Data Index: 2240150 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8664. Min Range: -2.8664
Max Act: 2.6429. Min Act: -0.1700
Data Index: 5177895 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #19