Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 12 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1497. Min Range: -4.1497
Max Act: 4.1497. Min Act: -0.1700
Data Index: 3045379 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1497. Min Range: -4.1497
Max Act: 4.1497. Min Act: -0.1700
Data Index: 2733914 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1497. Min Range: -4.1497
Max Act: 3.9934. Min Act: -0.1700
Data Index: 7863153 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1497. Min Range: -4.1497
Max Act: 4.0247. Min Act: -0.1700
Data Index: 2700259 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1497. Min Range: -4.1497
Max Act: 3.9934. Min Act: -0.1700
Data Index: 4633767 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1497. Min Range: -4.1497
Max Act: 4.0247. Min Act: -0.1700
Data Index: 4312518 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1497. Min Range: -4.1497
Max Act: 3.9934. Min Act: -0.1700
Data Index: 5511589 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1497. Min Range: -4.1497
Max Act: 3.9934. Min Act: -0.1700
Data Index: 7258047 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1497. Min Range: -4.1497
Max Act: 3.9934. Min Act: -0.1700
Data Index: 5946903 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1497. Min Range: -4.1497
Max Act: 3.9622. Min Act: -0.1700
Data Index: 787490 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1497. Min Range: -4.1497
Max Act: 3.9622. Min Act: -0.1700
Data Index: 6234504 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1497. Min Range: -4.1497
Max Act: 3.9622. Min Act: -0.1700
Data Index: 1156197 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1497. Min Range: -4.1497
Max Act: 3.9622. Min Act: -0.1700
Data Index: 1823890 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1497. Min Range: -4.1497
Max Act: 3.9622. Min Act: -0.1700
Data Index: 129443 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1497. Min Range: -4.1497
Max Act: 3.9622. Min Act: -0.1700
Data Index: 15033 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1497. Min Range: -4.1497
Max Act: 3.9622. Min Act: -0.1700
Data Index: 5327001 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1497. Min Range: -4.1497
Max Act: 3.9309. Min Act: -0.1700
Data Index: 7674136 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1497. Min Range: -4.1497
Max Act: 3.9309. Min Act: -0.1700
Data Index: 7831027 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1497. Min Range: -4.1497
Max Act: 3.9622. Min Act: -0.1700
Data Index: 4719588 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1497. Min Range: -4.1497
Max Act: 3.9309. Min Act: -0.1700
Data Index: 5724858 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19