Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2512 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9905. Min Range: -2.9905
Max Act: 2.9905. Min Act: -0.1700
Data Index: 8585772 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9905. Min Range: -2.9905
Max Act: 2.8002. Min Act: -0.1700
Data Index: 2911856 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9905. Min Range: -2.9905
Max Act: 2.8002. Min Act: -0.1700
Data Index: 8192701 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9905. Min Range: -2.9905
Max Act: 2.8002. Min Act: -0.1700
Data Index: 1888077 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9905. Min Range: -2.9905
Max Act: 2.7842. Min Act: -0.1700
Data Index: 6434881 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9905. Min Range: -2.9905
Max Act: 2.7842. Min Act: -0.1700
Data Index: 1105267 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9905. Min Range: -2.9905
Max Act: 2.7683. Min Act: -0.1700
Data Index: 1143470 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9905. Min Range: -2.9905
Max Act: 2.7683. Min Act: -0.1700
Data Index: 6144262 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9905. Min Range: -2.9905
Max Act: 2.7683. Min Act: -0.1700
Data Index: 3429609 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9905. Min Range: -2.9905
Max Act: 2.7364. Min Act: -0.1700
Data Index: 2325580 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9905. Min Range: -2.9905
Max Act: 2.7364. Min Act: -0.1700
Data Index: 3719274 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9905. Min Range: -2.9905
Max Act: 2.7204. Min Act: -0.1700
Data Index: 1825130 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9905. Min Range: -2.9905
Max Act: 2.7364. Min Act: -0.1700
Data Index: 5728064 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9905. Min Range: -2.9905
Max Act: 2.7523. Min Act: -0.1700
Data Index: 8510385 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9905. Min Range: -2.9905
Max Act: 2.7364. Min Act: -0.1700
Data Index: 1447050 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9905. Min Range: -2.9905
Max Act: 2.7204. Min Act: -0.1700
Data Index: 8818555 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9905. Min Range: -2.9905
Max Act: 2.6884. Min Act: -0.1700
Data Index: 8270928 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9905. Min Range: -2.9905
Max Act: 2.7364. Min Act: -0.1700
Data Index: 1198552 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9905. Min Range: -2.9905
Max Act: 2.7044. Min Act: -0.1700
Data Index: 2388075 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9905. Min Range: -2.9905
Max Act: 2.7204. Min Act: -0.1700
Data Index: 4241940 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #19