Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2532 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3497. Min Range: -4.3497
Max Act: 4.3497. Min Act: -0.1700
Data Index: 1317136 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3497. Min Range: -4.3497
Max Act: 4.0371. Min Act: -0.1700
Data Index: 2539971 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3497. Min Range: -4.3497
Max Act: 4.0059. Min Act: -0.1700
Data Index: 7231271 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3497. Min Range: -4.3497
Max Act: 3.9433. Min Act: -0.1700
Data Index: 7782657 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3497. Min Range: -4.3497
Max Act: 3.8808. Min Act: -0.1700
Data Index: 6184598 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3497. Min Range: -4.3497
Max Act: 3.9121. Min Act: -0.1700
Data Index: 8028044 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3497. Min Range: -4.3497
Max Act: 3.8495. Min Act: -0.1700
Data Index: 5551967 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3497. Min Range: -4.3497
Max Act: 3.8495. Min Act: -0.1700
Data Index: 5739396 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3497. Min Range: -4.3497
Max Act: 3.8495. Min Act: -0.1700
Data Index: 2828707 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3497. Min Range: -4.3497
Max Act: 3.8495. Min Act: -0.1700
Data Index: 351102 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3497. Min Range: -4.3497
Max Act: 3.8495. Min Act: -0.1700
Data Index: 6531747 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3497. Min Range: -4.3497
Max Act: 3.8495. Min Act: -0.1700
Data Index: 8024246 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3497. Min Range: -4.3497
Max Act: 3.8183. Min Act: -0.1700
Data Index: 3732338 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3497. Min Range: -4.3497
Max Act: 3.7870. Min Act: -0.1700
Data Index: 6008568 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3497. Min Range: -4.3497
Max Act: 3.6932. Min Act: -0.1700
Data Index: 3437589 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3497. Min Range: -4.3497
Max Act: 3.7870. Min Act: -0.1700
Data Index: 6506115 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3497. Min Range: -4.3497
Max Act: 3.7557. Min Act: -0.1700
Data Index: 783520 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3497. Min Range: -4.3497
Max Act: 3.7557. Min Act: -0.1700
Data Index: 5065802 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3497. Min Range: -4.3497
Max Act: 3.7244. Min Act: -0.1700
Data Index: 4299212 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3497. Min Range: -4.3497
Max Act: 3.7244. Min Act: -0.1700
Data Index: 3765885 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19