Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2657 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1537. Min Range: -5.1537
Max Act: 5.1537. Min Act: -0.1700
Data Index: 7484102 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1537. Min Range: -5.1537
Max Act: 5.1537. Min Act: -0.1700
Data Index: 1161797 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1537. Min Range: -5.1537
Max Act: 5.1537. Min Act: -0.1700
Data Index: 4496043 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1537. Min Range: -5.1537
Max Act: 5.0912. Min Act: -0.1700
Data Index: 6220160 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1537. Min Range: -5.1537
Max Act: 5.0912. Min Act: -0.1700
Data Index: 2898531 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1537. Min Range: -5.1537
Max Act: 5.0912. Min Act: -0.1700
Data Index: 2591559 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1537. Min Range: -5.1537
Max Act: 5.0287. Min Act: -0.1700
Data Index: 3927148 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1537. Min Range: -5.1537
Max Act: 5.0599. Min Act: -0.1700
Data Index: 4369923 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1537. Min Range: -5.1537
Max Act: 5.0287. Min Act: -0.1700
Data Index: 8239979 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1537. Min Range: -5.1537
Max Act: 5.0599. Min Act: -0.1700
Data Index: 1873397 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1537. Min Range: -5.1537
Max Act: 5.0287. Min Act: -0.1700
Data Index: 82921 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1537. Min Range: -5.1537
Max Act: 4.9974. Min Act: -0.1700
Data Index: 3307465 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1537. Min Range: -5.1537
Max Act: 4.9974. Min Act: -0.1700
Data Index: 6827873 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1537. Min Range: -5.1537
Max Act: 4.9974. Min Act: -0.1700
Data Index: 2204070 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1537. Min Range: -5.1537
Max Act: 4.9662. Min Act: -0.1700
Data Index: 1234606 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1537. Min Range: -5.1537
Max Act: 4.9974. Min Act: -0.1700
Data Index: 4252208 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1537. Min Range: -5.1537
Max Act: 4.9974. Min Act: -0.1700
Data Index: 94218 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1537. Min Range: -5.1537
Max Act: 4.9974. Min Act: -0.1700
Data Index: 5060502 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1537. Min Range: -5.1537
Max Act: 5.0287. Min Act: -0.1700
Data Index: 7974636 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1537. Min Range: -5.1537
Max Act: 4.9662. Min Act: -0.1700
Data Index: 8133066 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19