Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3654 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3515. Min Range: -3.3515
Max Act: 3.3515. Min Act: -0.1700
Data Index: 7530938 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3515. Min Range: -3.3515
Max Act: 3.3359. Min Act: -0.1700
Data Index: 4157531 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3515. Min Range: -3.3515
Max Act: 3.2888. Min Act: -0.1700
Data Index: 7964044 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3515. Min Range: -3.3515
Max Act: 3.3202. Min Act: -0.1700
Data Index: 3543935 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3515. Min Range: -3.3515
Max Act: 3.2731. Min Act: -0.1700
Data Index: 1076596 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3515. Min Range: -3.3515
Max Act: 3.2574. Min Act: -0.1700
Data Index: 5966024 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3515. Min Range: -3.3515
Max Act: 3.2416. Min Act: -0.1700
Data Index: 3436504 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3515. Min Range: -3.3515
Max Act: 3.2259. Min Act: -0.1700
Data Index: 2660101 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3515. Min Range: -3.3515
Max Act: 3.2102. Min Act: -0.1700
Data Index: 5764092 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3515. Min Range: -3.3515
Max Act: 3.1945. Min Act: -0.1700
Data Index: 4815870 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3515. Min Range: -3.3515
Max Act: 3.2102. Min Act: -0.1700
Data Index: 3594466 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3515. Min Range: -3.3515
Max Act: 3.1945. Min Act: -0.1700
Data Index: 3124942 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3515. Min Range: -3.3515
Max Act: 3.1945. Min Act: -0.1700
Data Index: 2218253 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3515. Min Range: -3.3515
Max Act: 3.1787. Min Act: -0.1700
Data Index: 4418951 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3515. Min Range: -3.3515
Max Act: 3.1945. Min Act: -0.1700
Data Index: 1205527 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3515. Min Range: -3.3515
Max Act: 3.2102. Min Act: -0.1700
Data Index: 8132773 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3515. Min Range: -3.3515
Max Act: 3.1630. Min Act: -0.1700
Data Index: 8218928 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3515. Min Range: -3.3515
Max Act: 3.1787. Min Act: -0.1700
Data Index: 1947611 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3515. Min Range: -3.3515
Max Act: 3.1787. Min Act: -0.1700
Data Index: 83267 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3515. Min Range: -3.3515
Max Act: 3.1787. Min Act: -0.1700
Data Index: 2329586 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19