Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3104 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2489. Min Range: -3.2489
Max Act: 3.2489. Min Act: -0.1700
Data Index: 6387659 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2489. Min Range: -3.2489
Max Act: 3.1860. Min Act: -0.1700
Data Index: 8147243 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2489. Min Range: -3.2489
Max Act: 3.1388. Min Act: -0.1700
Data Index: 3165296 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2489. Min Range: -3.2489
Max Act: 3.1388. Min Act: -0.1700
Data Index: 3589520 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2489. Min Range: -3.2489
Max Act: 3.1545. Min Act: -0.1700
Data Index: 7341760 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2489. Min Range: -3.2489
Max Act: 3.1230. Min Act: -0.1700
Data Index: 19670 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2489. Min Range: -3.2489
Max Act: 3.1073. Min Act: -0.1700
Data Index: 3409478 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2489. Min Range: -3.2489
Max Act: 3.1073. Min Act: -0.1700
Data Index: 4414128 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2489. Min Range: -3.2489
Max Act: 3.1230. Min Act: -0.1700
Data Index: 731683 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2489. Min Range: -3.2489
Max Act: 3.1073. Min Act: -0.1700
Data Index: 8497655 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2489. Min Range: -3.2489
Max Act: 3.0915. Min Act: -0.1700
Data Index: 8848 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2489. Min Range: -3.2489
Max Act: 3.0915. Min Act: -0.1700
Data Index: 5639073 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2489. Min Range: -3.2489
Max Act: 3.1073. Min Act: -0.1700
Data Index: 3216863 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2489. Min Range: -3.2489
Max Act: 3.0757. Min Act: -0.1700
Data Index: 5126532 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2489. Min Range: -3.2489
Max Act: 3.0915. Min Act: -0.1700
Data Index: 8021254 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2489. Min Range: -3.2489
Max Act: 3.0915. Min Act: -0.1700
Data Index: 4959194 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2489. Min Range: -3.2489
Max Act: 3.0915. Min Act: -0.1700
Data Index: 4138173 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2489. Min Range: -3.2489
Max Act: 3.0915. Min Act: -0.1700
Data Index: 7265856 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2489. Min Range: -3.2489
Max Act: 3.0600. Min Act: -0.1700
Data Index: 208803 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2489. Min Range: -3.2489
Max Act: 3.0600. Min Act: -0.1700
Data Index: 5919889 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19