Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2144 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5138. Min Range: -7.5138
Max Act: 7.4825. Min Act: -0.1700
Data Index: 5249314 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5138. Min Range: -7.5138
Max Act: 7.5138. Min Act: -0.1700
Data Index: 7414475 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5138. Min Range: -7.5138
Max Act: 7.3263. Min Act: -0.1700
Data Index: 4840872 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5138. Min Range: -7.5138
Max Act: 7.2325. Min Act: -0.1700
Data Index: 3381281 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5138. Min Range: -7.5138
Max Act: 7.2013. Min Act: -0.1700
Data Index: 7993316 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5138. Min Range: -7.5138
Max Act: 7.2013. Min Act: -0.1700
Data Index: 7126953 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5138. Min Range: -7.5138
Max Act: 7.1700. Min Act: -0.1700
Data Index: 2081004 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5138. Min Range: -7.5138
Max Act: 7.1075. Min Act: -0.1700
Data Index: 1175767 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5138. Min Range: -7.5138
Max Act: 7.1388. Min Act: -0.1700
Data Index: 6800322 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5138. Min Range: -7.5138
Max Act: 7.1388. Min Act: -0.1700
Data Index: 457375 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5138. Min Range: -7.5138
Max Act: 7.1388. Min Act: -0.1700
Data Index: 3994098 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5138. Min Range: -7.5138
Max Act: 7.0763. Min Act: -0.1700
Data Index: 4707976 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5138. Min Range: -7.5138
Max Act: 7.1075. Min Act: -0.1700
Data Index: 7296225 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5138. Min Range: -7.5138
Max Act: 7.0450. Min Act: -0.1700
Data Index: 6486912 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5138. Min Range: -7.5138
Max Act: 7.0450. Min Act: -0.1700
Data Index: 3130389 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5138. Min Range: -7.5138
Max Act: 7.0138. Min Act: -0.1700
Data Index: 2965972 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5138. Min Range: -7.5138
Max Act: 6.9825. Min Act: -0.1700
Data Index: 957829 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5138. Min Range: -7.5138
Max Act: 6.9825. Min Act: -0.1700
Data Index: 3386182 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5138. Min Range: -7.5138
Max Act: 6.9513. Min Act: -0.1700
Data Index: 912368 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5138. Min Range: -7.5138
Max Act: 6.8888. Min Act: -0.1700
Data Index: 1492991 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #19