Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3451 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8291. Min Range: -1.8291
Max Act: 1.8291. Min Act: -0.1700
Data Index: 4560006 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8291. Min Range: -1.8291
Max Act: 1.7861. Min Act: -0.1700
Data Index: 6159132 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8291. Min Range: -1.8291
Max Act: 1.7689. Min Act: -0.1700
Data Index: 2664152 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8291. Min Range: -1.8291
Max Act: 1.7516. Min Act: -0.1700
Data Index: 990703 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8291. Min Range: -1.8291
Max Act: 1.7516. Min Act: -0.1700
Data Index: 4744036 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8291. Min Range: -1.8291
Max Act: 1.7430. Min Act: -0.1700
Data Index: 7290390 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8291. Min Range: -1.8291
Max Act: 1.7516. Min Act: -0.1700
Data Index: 2657378 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8291. Min Range: -1.8291
Max Act: 1.7430. Min Act: -0.1700
Data Index: 1158650 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8291. Min Range: -1.8291
Max Act: 1.7430. Min Act: -0.1700
Data Index: 4623807 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8291. Min Range: -1.8291
Max Act: 1.7343. Min Act: -0.1700
Data Index: 2362531 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8291. Min Range: -1.8291
Max Act: 1.7343. Min Act: -0.1700
Data Index: 4132279 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8291. Min Range: -1.8291
Max Act: 1.7343. Min Act: -0.1700
Data Index: 6268531 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8291. Min Range: -1.8291
Max Act: 1.7343. Min Act: -0.1700
Data Index: 850787 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8291. Min Range: -1.8291
Max Act: 1.7257. Min Act: -0.1700
Data Index: 6784853 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8291. Min Range: -1.8291
Max Act: 1.7257. Min Act: -0.1700
Data Index: 1816374 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8291. Min Range: -1.8291
Max Act: 1.7257. Min Act: -0.1700
Data Index: 8742750 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8291. Min Range: -1.8291
Max Act: 1.7170. Min Act: -0.1700
Data Index: 7087099 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8291. Min Range: -1.8291
Max Act: 1.7084. Min Act: -0.1700
Data Index: 652200 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8291. Min Range: -1.8291
Max Act: 1.6997. Min Act: -0.1699
Data Index: 4513245 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8291. Min Range: -1.8291
Max Act: 1.6997. Min Act: -0.1700
Data Index: 7087100 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19