Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2304 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6210. Min Range: -6.6210
Max Act: 6.6210. Min Act: -0.1700
Data Index: 7575528 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6210. Min Range: -6.6210
Max Act: 6.5272. Min Act: -0.1700
Data Index: 2454990 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6210. Min Range: -6.6210
Max Act: 6.4647. Min Act: -0.1700
Data Index: 1724332 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6210. Min Range: -6.6210
Max Act: 6.4335. Min Act: -0.1700
Data Index: 8734954 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6210. Min Range: -6.6210
Max Act: 6.4647. Min Act: -0.1700
Data Index: 3174473 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6210. Min Range: -6.6210
Max Act: 6.4647. Min Act: -0.1700
Data Index: 5632830 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6210. Min Range: -6.6210
Max Act: 6.4647. Min Act: -0.1700
Data Index: 8533373 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6210. Min Range: -6.6210
Max Act: 6.4647. Min Act: -0.1700
Data Index: 8361198 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6210. Min Range: -6.6210
Max Act: 6.4647. Min Act: -0.1700
Data Index: 7970227 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6210. Min Range: -6.6210
Max Act: 6.4022. Min Act: -0.1700
Data Index: 3865900 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6210. Min Range: -6.6210
Max Act: 6.4022. Min Act: -0.1700
Data Index: 3397668 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6210. Min Range: -6.6210
Max Act: 6.4022. Min Act: -0.1700
Data Index: 8798652 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6210. Min Range: -6.6210
Max Act: 6.3710. Min Act: -0.1700
Data Index: 2417743 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6210. Min Range: -6.6210
Max Act: 6.3710. Min Act: -0.1700
Data Index: 5472171 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6210. Min Range: -6.6210
Max Act: 6.3710. Min Act: -0.1700
Data Index: 148489 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6210. Min Range: -6.6210
Max Act: 6.3710. Min Act: -0.1700
Data Index: 5871107 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6210. Min Range: -6.6210
Max Act: 6.3710. Min Act: -0.1700
Data Index: 777235 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6210. Min Range: -6.6210
Max Act: 6.3397. Min Act: -0.1700
Data Index: 551679 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6210. Min Range: -6.6210
Max Act: 6.3397. Min Act: -0.1700
Data Index: 67332 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6210. Min Range: -6.6210
Max Act: 6.3085. Min Act: -0.1700
Data Index: 7845143 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #19