Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1374 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.8808. Min Act: -0.1700
Data Index: 95256 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.8808. Min Act: -0.1700
Data Index: 2761526 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.8808. Min Act: -0.1700
Data Index: 7454141 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.8637. Min Act: -0.1700
Data Index: 2046390 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.8637. Min Act: -0.1700
Data Index: 3773311 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.8637. Min Act: -0.1700
Data Index: 917250 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.8637. Min Act: -0.1700
Data Index: 1351428 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.8637. Min Act: -0.1700
Data Index: 3424282 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.8466. Min Act: -0.1699
Data Index: 775311 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.8466. Min Act: -0.1700
Data Index: 5254261 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.8380. Min Act: -0.1700
Data Index: 4429862 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.8380. Min Act: -0.1700
Data Index: 1096906 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.8551. Min Act: -0.1700
Data Index: 756841 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.8380. Min Act: -0.1700
Data Index: 1839293 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.8466. Min Act: -0.1700
Data Index: 2432027 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.8380. Min Act: -0.1700
Data Index: 4978539 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.8380. Min Act: -0.1700
Data Index: 4866519 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.8380. Min Act: -0.1700
Data Index: 1055238 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.8294. Min Act: -0.1700
Data Index: 5063293 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.8380. Min Act: -0.1700
Data Index: 7958292 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #19