Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 562 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9006. Min Range: -2.9006
Max Act: 2.9006. Min Act: -0.1700
Data Index: 4264766 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9006. Min Range: -2.9006
Max Act: 2.8688. Min Act: -0.1700
Data Index: 8502916 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9006. Min Range: -2.9006
Max Act: 2.8370. Min Act: -0.1700
Data Index: 6835357 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9006. Min Range: -2.9006
Max Act: 2.7574. Min Act: -0.1700
Data Index: 7411607 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9006. Min Range: -2.9006
Max Act: 2.7574. Min Act: -0.1700
Data Index: 5698412 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9006. Min Range: -2.9006
Max Act: 2.7095. Min Act: -0.1700
Data Index: 2033391 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9006. Min Range: -2.9006
Max Act: 2.7734. Min Act: -0.1700
Data Index: 7951704 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9006. Min Range: -2.9006
Max Act: 2.7414. Min Act: -0.1700
Data Index: 3584341 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9006. Min Range: -2.9006
Max Act: 2.7893. Min Act: -0.1700
Data Index: 3371826 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9006. Min Range: -2.9006
Max Act: 2.7414. Min Act: -0.1700
Data Index: 1614696 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9006. Min Range: -2.9006
Max Act: 2.7414. Min Act: -0.1700
Data Index: 6835354 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9006. Min Range: -2.9006
Max Act: 2.7255. Min Act: -0.1700
Data Index: 1303884 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9006. Min Range: -2.9006
Max Act: 2.7095. Min Act: -0.1700
Data Index: 3326221 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9006. Min Range: -2.9006
Max Act: 2.7095. Min Act: -0.1700
Data Index: 4063400 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9006. Min Range: -2.9006
Max Act: 2.7255. Min Act: -0.1700
Data Index: 3880916 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9006. Min Range: -2.9006
Max Act: 2.7095. Min Act: -0.1700
Data Index: 4340340 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9006. Min Range: -2.9006
Max Act: 2.7095. Min Act: -0.1700
Data Index: 1546520 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9006. Min Range: -2.9006
Max Act: 2.7095. Min Act: -0.1700
Data Index: 6240239 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9006. Min Range: -2.9006
Max Act: 2.6775. Min Act: -0.1700
Data Index: 4523185 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9006. Min Range: -2.9006
Max Act: 2.6935. Min Act: -0.1700
Data Index: 803512 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #19