Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2019 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.9952. Min Range: -7.9952
Max Act: 7.9952. Min Act: -0.1700
Data Index: 3110278 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9952. Min Range: -7.9952
Max Act: 7.9015. Min Act: -0.1700
Data Index: 5003595 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9952. Min Range: -7.9952
Max Act: 7.8390. Min Act: -0.1700
Data Index: 8569902 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9952. Min Range: -7.9952
Max Act: 7.5577. Min Act: -0.1700
Data Index: 4165387 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9952. Min Range: -7.9952
Max Act: 7.6202. Min Act: -0.1700
Data Index: 7830662 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9952. Min Range: -7.9952
Max Act: 7.4952. Min Act: -0.1700
Data Index: 277434 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9952. Min Range: -7.9952
Max Act: 7.4640. Min Act: -0.1700
Data Index: 8182790 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9952. Min Range: -7.9952
Max Act: 7.4952. Min Act: -0.1700
Data Index: 7318038 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9952. Min Range: -7.9952
Max Act: 7.5890. Min Act: -0.1700
Data Index: 4537787 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9952. Min Range: -7.9952
Max Act: 7.4640. Min Act: -0.1700
Data Index: 5457304 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9952. Min Range: -7.9952
Max Act: 7.4640. Min Act: -0.1700
Data Index: 8301573 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9952. Min Range: -7.9952
Max Act: 7.4952. Min Act: -0.1700
Data Index: 8795988 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9952. Min Range: -7.9952
Max Act: 7.3702. Min Act: -0.1700
Data Index: 2621596 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9952. Min Range: -7.9952
Max Act: 7.4327. Min Act: -0.1700
Data Index: 1343737 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9952. Min Range: -7.9952
Max Act: 7.3702. Min Act: -0.1700
Data Index: 5457315 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9952. Min Range: -7.9952
Max Act: 7.3390. Min Act: -0.1700
Data Index: 3348466 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9952. Min Range: -7.9952
Max Act: 7.2765. Min Act: -0.1700
Data Index: 4569805 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9952. Min Range: -7.9952
Max Act: 7.3390. Min Act: -0.1700
Data Index: 1153935 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9952. Min Range: -7.9952
Max Act: 7.2765. Min Act: -0.1700
Data Index: 3348477 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9952. Min Range: -7.9952
Max Act: 7.2140. Min Act: -0.1700
Data Index: 7487401 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #19