Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 250 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7690. Min Range: -1.7690
Max Act: 1.7690. Min Act: -0.1700
Data Index: 5161072 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7690. Min Range: -1.7690
Max Act: 1.3494. Min Act: -0.1700
Data Index: 8047721 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7690. Min Range: -1.7690
Max Act: 1.3317. Min Act: -0.1700
Data Index: 8176402 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7690. Min Range: -1.7690
Max Act: 1.2965. Min Act: -0.1700
Data Index: 1151328 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7690. Min Range: -1.7690
Max Act: 1.2965. Min Act: -0.1700
Data Index: 1151329 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7690. Min Range: -1.7690
Max Act: 1.2965. Min Act: -0.1700
Data Index: 7971094 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7690. Min Range: -1.7690
Max Act: 1.2965. Min Act: -0.1700
Data Index: 4341540 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7690. Min Range: -1.7690
Max Act: 1.2612. Min Act: -0.1700
Data Index: 7563646 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7690. Min Range: -1.7690
Max Act: 1.2436. Min Act: -0.1700
Data Index: 7563645 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7690. Min Range: -1.7690
Max Act: 1.2612. Min Act: -0.1700
Data Index: 8031817 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7690. Min Range: -1.7690
Max Act: 1.2436. Min Act: -0.1700
Data Index: 1655588 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7690. Min Range: -1.7690
Max Act: 1.2436. Min Act: -0.1700
Data Index: 5504716 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7690. Min Range: -1.7690
Max Act: 1.2259. Min Act: -0.1700
Data Index: 1893974 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7690. Min Range: -1.7690
Max Act: 1.2436. Min Act: -0.1700
Data Index: 622076 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7690. Min Range: -1.7690
Max Act: 1.2259. Min Act: -0.1700
Data Index: 7474701 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7690. Min Range: -1.7690
Max Act: 1.2259. Min Act: -0.1700
Data Index: 6801589 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7690. Min Range: -1.7690
Max Act: 1.2083. Min Act: -0.1700
Data Index: 3619943 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7690. Min Range: -1.7690
Max Act: 1.2259. Min Act: -0.1700
Data Index: 7525371 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7690. Min Range: -1.7690
Max Act: 1.2083. Min Act: -0.1700
Data Index: 6387427 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7690. Min Range: -1.7690
Max Act: 1.2259. Min Act: -0.1700
Data Index: 1695958 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19