Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1720 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1932. Min Range: -6.1932
Max Act: 6.1932. Min Act: -0.1700
Data Index: 5819443 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1932. Min Range: -6.1932
Max Act: 6.1619. Min Act: -0.1700
Data Index: 565088 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1932. Min Range: -6.1932
Max Act: 6.0057. Min Act: -0.1700
Data Index: 2188744 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1932. Min Range: -6.1932
Max Act: 6.0057. Min Act: -0.1700
Data Index: 4285316 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1932. Min Range: -6.1932
Max Act: 5.9744. Min Act: -0.1700
Data Index: 2910580 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1932. Min Range: -6.1932
Max Act: 5.9119. Min Act: -0.1700
Data Index: 7691611 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1932. Min Range: -6.1932
Max Act: 5.8807. Min Act: -0.1700
Data Index: 400024 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1932. Min Range: -6.1932
Max Act: 5.9119. Min Act: -0.1700
Data Index: 798755 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1932. Min Range: -6.1932
Max Act: 5.8807. Min Act: -0.1700
Data Index: 2833386 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1932. Min Range: -6.1932
Max Act: 5.8807. Min Act: -0.1700
Data Index: 683244 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1932. Min Range: -6.1932
Max Act: 5.9119. Min Act: -0.1700
Data Index: 3110072 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1932. Min Range: -6.1932
Max Act: 5.8494. Min Act: -0.1700
Data Index: 5231238 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1932. Min Range: -6.1932
Max Act: 5.8494. Min Act: -0.1700
Data Index: 3692183 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1932. Min Range: -6.1932
Max Act: 5.8494. Min Act: -0.1700
Data Index: 2114186 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1932. Min Range: -6.1932
Max Act: 5.8494. Min Act: -0.1700
Data Index: 55514 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1932. Min Range: -6.1932
Max Act: 5.8807. Min Act: -0.1700
Data Index: 4333705 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1932. Min Range: -6.1932
Max Act: 5.8494. Min Act: -0.1700
Data Index: 3563405 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1932. Min Range: -6.1932
Max Act: 5.8182. Min Act: -0.1700
Data Index: 6870276 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1932. Min Range: -6.1932
Max Act: 5.7869. Min Act: -0.1700
Data Index: 7640147 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1932. Min Range: -6.1932
Max Act: 5.8494. Min Act: -0.1700
Data Index: 1241808 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #19