Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1824 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3026. Min Range: -6.3026
Max Act: 6.3026. Min Act: -0.1700
Data Index: 2164054 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3026. Min Range: -6.3026
Max Act: 5.9588. Min Act: -0.1700
Data Index: 5667883 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3026. Min Range: -6.3026
Max Act: 5.9276. Min Act: -0.1700
Data Index: 1857169 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3026. Min Range: -6.3026
Max Act: 5.8651. Min Act: -0.1700
Data Index: 8023289 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3026. Min Range: -6.3026
Max Act: 5.8651. Min Act: -0.1700
Data Index: 1444965 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3026. Min Range: -6.3026
Max Act: 5.8338. Min Act: -0.1700
Data Index: 7728089 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3026. Min Range: -6.3026
Max Act: 5.8338. Min Act: -0.1700
Data Index: 6008527 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3026. Min Range: -6.3026
Max Act: 5.8338. Min Act: -0.1700
Data Index: 4770991 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3026. Min Range: -6.3026
Max Act: 5.8026. Min Act: -0.1700
Data Index: 7010405 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3026. Min Range: -6.3026
Max Act: 5.7713. Min Act: -0.1700
Data Index: 4926597 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3026. Min Range: -6.3026
Max Act: 5.7401. Min Act: -0.1700
Data Index: 2196942 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3026. Min Range: -6.3026
Max Act: 5.7088. Min Act: -0.1700
Data Index: 4290470 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3026. Min Range: -6.3026
Max Act: 5.7401. Min Act: -0.1700
Data Index: 2096434 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3026. Min Range: -6.3026
Max Act: 5.6776. Min Act: -0.1700
Data Index: 4683090 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3026. Min Range: -6.3026
Max Act: 5.7088. Min Act: -0.1700
Data Index: 638877 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3026. Min Range: -6.3026
Max Act: 5.7088. Min Act: -0.1700
Data Index: 5672852 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3026. Min Range: -6.3026
Max Act: 5.7088. Min Act: -0.1700
Data Index: 3576845 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3026. Min Range: -6.3026
Max Act: 5.7088. Min Act: -0.1700
Data Index: 7641606 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3026. Min Range: -6.3026
Max Act: 5.7401. Min Act: -0.1700
Data Index: 1835772 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3026. Min Range: -6.3026
Max Act: 5.7088. Min Act: -0.1700
Data Index: 6514996 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #19