Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3959 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7566. Min Range: -5.7566
Max Act: 5.7566. Min Act: -0.1700
Data Index: 1169089 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7566. Min Range: -5.7566
Max Act: 5.4754. Min Act: -0.1700
Data Index: 993244 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7566. Min Range: -5.7566
Max Act: 5.5066. Min Act: -0.1700
Data Index: 5416550 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7566. Min Range: -5.7566
Max Act: 5.4441. Min Act: -0.1700
Data Index: 5895034 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7566. Min Range: -5.7566
Max Act: 5.4129. Min Act: -0.1700
Data Index: 7946672 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7566. Min Range: -5.7566
Max Act: 5.3191. Min Act: -0.1700
Data Index: 1474303 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7566. Min Range: -5.7566
Max Act: 5.3191. Min Act: -0.1700
Data Index: 2450371 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7566. Min Range: -5.7566
Max Act: 5.3191. Min Act: -0.1700
Data Index: 4846049 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7566. Min Range: -5.7566
Max Act: 5.3191. Min Act: -0.1700
Data Index: 8441799 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7566. Min Range: -5.7566
Max Act: 5.3191. Min Act: -0.1700
Data Index: 1237685 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7566. Min Range: -5.7566
Max Act: 5.2879. Min Act: -0.1700
Data Index: 7296088 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7566. Min Range: -5.7566
Max Act: 5.2254. Min Act: -0.1700
Data Index: 20716 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7566. Min Range: -5.7566
Max Act: 5.1941. Min Act: -0.1700
Data Index: 3891251 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7566. Min Range: -5.7566
Max Act: 5.1941. Min Act: -0.1700
Data Index: 7471851 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7566. Min Range: -5.7566
Max Act: 5.1941. Min Act: -0.1700
Data Index: 402657 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7566. Min Range: -5.7566
Max Act: 5.1941. Min Act: -0.1700
Data Index: 4180578 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7566. Min Range: -5.7566
Max Act: 5.1316. Min Act: -0.1700
Data Index: 4831506 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7566. Min Range: -5.7566
Max Act: 5.1004. Min Act: -0.1700
Data Index: 5966779 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7566. Min Range: -5.7566
Max Act: 5.1316. Min Act: -0.1700
Data Index: 4764552 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7566. Min Range: -5.7566
Max Act: 5.1629. Min Act: -0.1700
Data Index: 624414 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19