Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3191 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.8329. Min Range: -7.8329
Max Act: 7.8329. Min Act: -0.1700
Data Index: 5736279 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8329. Min Range: -7.8329
Max Act: 7.7392. Min Act: -0.1700
Data Index: 5736284 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8329. Min Range: -7.8329
Max Act: 6.9892. Min Act: -0.1700
Data Index: 502310 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8329. Min Range: -7.8329
Max Act: 6.9892. Min Act: -0.1700
Data Index: 436540 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8329. Min Range: -7.8329
Max Act: 6.9579. Min Act: -0.1700
Data Index: 3159937 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8329. Min Range: -7.8329
Max Act: 6.8642. Min Act: -0.1700
Data Index: 3947309 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8329. Min Range: -7.8329
Max Act: 6.8954. Min Act: -0.1700
Data Index: 1592054 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8329. Min Range: -7.8329
Max Act: 6.8329. Min Act: -0.1700
Data Index: 2327605 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8329. Min Range: -7.8329
Max Act: 6.8017. Min Act: -0.1700
Data Index: 6678058 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8329. Min Range: -7.8329
Max Act: 6.8642. Min Act: -0.1700
Data Index: 4530371 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8329. Min Range: -7.8329
Max Act: 6.8329. Min Act: -0.1700
Data Index: 7978136 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8329. Min Range: -7.8329
Max Act: 6.7704. Min Act: -0.1700
Data Index: 7740231 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8329. Min Range: -7.8329
Max Act: 6.8329. Min Act: -0.1700
Data Index: 2655858 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8329. Min Range: -7.8329
Max Act: 6.8017. Min Act: -0.1700
Data Index: 1397529 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8329. Min Range: -7.8329
Max Act: 6.8017. Min Act: -0.1700
Data Index: 7429507 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8329. Min Range: -7.8329
Max Act: 6.8329. Min Act: -0.1700
Data Index: 7000883 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8329. Min Range: -7.8329
Max Act: 6.8017. Min Act: -0.1700
Data Index: 2253035 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8329. Min Range: -7.8329
Max Act: 6.8329. Min Act: -0.1700
Data Index: 7170683 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8329. Min Range: -7.8329
Max Act: 6.7392. Min Act: -0.1700
Data Index: 5594515 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8329. Min Range: -7.8329
Max Act: 6.7704. Min Act: -0.1700
Data Index: 5883977 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19