Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2667 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7761. Min Range: -5.7761
Max Act: 5.7761. Min Act: -0.1700
Data Index: 5415284 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7761. Min Range: -5.7761
Max Act: 5.7136. Min Act: -0.1700
Data Index: 3781498 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7761. Min Range: -5.7761
Max Act: 5.6511. Min Act: -0.1700
Data Index: 7217999 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7761. Min Range: -5.7761
Max Act: 5.6198. Min Act: -0.1700
Data Index: 6234277 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7761. Min Range: -5.7761
Max Act: 5.6511. Min Act: -0.1700
Data Index: 492100 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7761. Min Range: -5.7761
Max Act: 5.5886. Min Act: -0.1700
Data Index: 3849975 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7761. Min Range: -5.7761
Max Act: 5.5261. Min Act: -0.1700
Data Index: 5518544 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7761. Min Range: -5.7761
Max Act: 5.5261. Min Act: -0.1700
Data Index: 7952059 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7761. Min Range: -5.7761
Max Act: 5.5261. Min Act: -0.1700
Data Index: 2422450 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7761. Min Range: -5.7761
Max Act: 5.4948. Min Act: -0.1700
Data Index: 7234792 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7761. Min Range: -5.7761
Max Act: 5.5573. Min Act: -0.1700
Data Index: 4580283 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7761. Min Range: -5.7761
Max Act: 5.4636. Min Act: -0.1700
Data Index: 4401959 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7761. Min Range: -5.7761
Max Act: 5.4636. Min Act: -0.1700
Data Index: 1814731 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7761. Min Range: -5.7761
Max Act: 5.4636. Min Act: -0.1700
Data Index: 6671727 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7761. Min Range: -5.7761
Max Act: 5.4323. Min Act: -0.1700
Data Index: 4170192 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7761. Min Range: -5.7761
Max Act: 5.4323. Min Act: -0.1700
Data Index: 4135024 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7761. Min Range: -5.7761
Max Act: 5.4323. Min Act: -0.1700
Data Index: 5499410 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7761. Min Range: -5.7761
Max Act: 5.4323. Min Act: -0.1700
Data Index: 1311683 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7761. Min Range: -5.7761
Max Act: 5.4011. Min Act: -0.1700
Data Index: 785654 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7761. Min Range: -5.7761
Max Act: 5.4011. Min Act: -0.1700
Data Index: 4059718 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19