Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3247 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0822. Min Range: -5.0822
Max Act: 5.0822. Min Act: -0.1700
Data Index: 5112378 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0822. Min Range: -5.0822
Max Act: 4.9259. Min Act: -0.1700
Data Index: 8619360 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0822. Min Range: -5.0822
Max Act: 4.8947. Min Act: -0.1700
Data Index: 1753456 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0822. Min Range: -5.0822
Max Act: 4.8634. Min Act: -0.1700
Data Index: 4051267 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0822. Min Range: -5.0822
Max Act: 4.8634. Min Act: -0.1700
Data Index: 8279101 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0822. Min Range: -5.0822
Max Act: 4.8322. Min Act: -0.1700
Data Index: 587854 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0822. Min Range: -5.0822
Max Act: 4.8322. Min Act: -0.1700
Data Index: 8501261 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0822. Min Range: -5.0822
Max Act: 4.8322. Min Act: -0.1700
Data Index: 1605190 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0822. Min Range: -5.0822
Max Act: 4.8322. Min Act: -0.1700
Data Index: 5085071 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0822. Min Range: -5.0822
Max Act: 4.8322. Min Act: -0.1700
Data Index: 2534845 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0822. Min Range: -5.0822
Max Act: 4.8009. Min Act: -0.1700
Data Index: 3817485 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0822. Min Range: -5.0822
Max Act: 4.8009. Min Act: -0.1700
Data Index: 2946374 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0822. Min Range: -5.0822
Max Act: 4.8009. Min Act: -0.1700
Data Index: 4677932 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0822. Min Range: -5.0822
Max Act: 4.8009. Min Act: -0.1700
Data Index: 409814 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0822. Min Range: -5.0822
Max Act: 4.8009. Min Act: -0.1700
Data Index: 7178735 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0822. Min Range: -5.0822
Max Act: 4.8009. Min Act: -0.1700
Data Index: 2296669 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0822. Min Range: -5.0822
Max Act: 4.7697. Min Act: -0.1700
Data Index: 8722624 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0822. Min Range: -5.0822
Max Act: 4.7697. Min Act: -0.1700
Data Index: 6827021 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0822. Min Range: -5.0822
Max Act: 4.7697. Min Act: -0.1700
Data Index: 3224181 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0822. Min Range: -5.0822
Max Act: 4.7384. Min Act: -0.1700
Data Index: 3844097 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #19