Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3376 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0155. Min Range: -5.0155
Max Act: 5.0155. Min Act: -0.1700
Data Index: 927169 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0155. Min Range: -5.0155
Max Act: 4.6717. Min Act: -0.1700
Data Index: 7202403 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0155. Min Range: -5.0155
Max Act: 4.6717. Min Act: -0.1700
Data Index: 7202400 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0155. Min Range: -5.0155
Max Act: 4.6405. Min Act: -0.1700
Data Index: 7202402 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0155. Min Range: -5.0155
Max Act: 4.6405. Min Act: -0.1700
Data Index: 7200869 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0155. Min Range: -5.0155
Max Act: 4.6405. Min Act: -0.1700
Data Index: 1170587 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0155. Min Range: -5.0155
Max Act: 4.5467. Min Act: -0.1700
Data Index: 4419593 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0155. Min Range: -5.0155
Max Act: 4.5155. Min Act: -0.1700
Data Index: 7202401 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0155. Min Range: -5.0155
Max Act: 4.5155. Min Act: -0.1700
Data Index: 4952920 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0155. Min Range: -5.0155
Max Act: 4.4530. Min Act: -0.1700
Data Index: 1307996 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0155. Min Range: -5.0155
Max Act: 4.4530. Min Act: -0.1700
Data Index: 8568489 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0155. Min Range: -5.0155
Max Act: 4.3905. Min Act: -0.1700
Data Index: 927168 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0155. Min Range: -5.0155
Max Act: 4.4530. Min Act: -0.1700
Data Index: 4731280 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0155. Min Range: -5.0155
Max Act: 4.3905. Min Act: -0.1700
Data Index: 7306861 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0155. Min Range: -5.0155
Max Act: 4.3905. Min Act: -0.1700
Data Index: 2990630 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0155. Min Range: -5.0155
Max Act: 4.3905. Min Act: -0.1700
Data Index: 1740360 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0155. Min Range: -5.0155
Max Act: 4.3592. Min Act: -0.1700
Data Index: 8049378 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0155. Min Range: -5.0155
Max Act: 4.3592. Min Act: -0.1700
Data Index: 1067026 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0155. Min Range: -5.0155
Max Act: 4.3592. Min Act: -0.1700
Data Index: 5773559 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0155. Min Range: -5.0155
Max Act: 4.3280. Min Act: -0.1700
Data Index: 5167395 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19