Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 5 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3476. Min Range: -4.3476
Max Act: 4.3164. Min Act: -0.1700
Data Index: 8615166 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3476. Min Range: -4.3476
Max Act: 4.3164. Min Act: -0.1700
Data Index: 3507507 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3476. Min Range: -4.3476
Max Act: 4.2226. Min Act: -0.1700
Data Index: 8238584 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3476. Min Range: -4.3476
Max Act: 4.3476. Min Act: -0.1700
Data Index: 151711 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3476. Min Range: -4.3476
Max Act: 4.2226. Min Act: -0.1700
Data Index: 8402389 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3476. Min Range: -4.3476
Max Act: 4.1913. Min Act: -0.1700
Data Index: 3319696 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3476. Min Range: -4.3476
Max Act: 4.1601. Min Act: -0.1700
Data Index: 4677514 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3476. Min Range: -4.3476
Max Act: 4.1288. Min Act: -0.1700
Data Index: 7346120 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3476. Min Range: -4.3476
Max Act: 4.1288. Min Act: -0.1700
Data Index: 6785669 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3476. Min Range: -4.3476
Max Act: 4.1288. Min Act: -0.1700
Data Index: 5829654 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3476. Min Range: -4.3476
Max Act: 4.0663. Min Act: -0.1700
Data Index: 2421613 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3476. Min Range: -4.3476
Max Act: 4.0663. Min Act: -0.1700
Data Index: 6167339 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3476. Min Range: -4.3476
Max Act: 4.0976. Min Act: -0.1700
Data Index: 4127350 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3476. Min Range: -4.3476
Max Act: 4.0351. Min Act: -0.1700
Data Index: 8073598 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3476. Min Range: -4.3476
Max Act: 4.0663. Min Act: -0.1700
Data Index: 3787746 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3476. Min Range: -4.3476
Max Act: 4.0663. Min Act: -0.1700
Data Index: 3520740 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3476. Min Range: -4.3476
Max Act: 4.0663. Min Act: -0.1700
Data Index: 3974052 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3476. Min Range: -4.3476
Max Act: 4.0351. Min Act: -0.1700
Data Index: 7159710 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3476. Min Range: -4.3476
Max Act: 4.0663. Min Act: -0.1700
Data Index: 7125597 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3476. Min Range: -4.3476
Max Act: 4.0351. Min Act: -0.1700
Data Index: 3986171 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #19