Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3112 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2668. Min Range: -3.2668
Max Act: 3.2668. Min Act: -0.1700
Data Index: 5962102 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2668. Min Range: -3.2668
Max Act: 3.1410. Min Act: -0.1700
Data Index: 2889761 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2668. Min Range: -3.2668
Max Act: 3.0779. Min Act: -0.1700
Data Index: 2470182 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2668. Min Range: -3.2668
Max Act: 3.0464. Min Act: -0.1700
Data Index: 7743819 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2668. Min Range: -3.2668
Max Act: 3.0622. Min Act: -0.1700
Data Index: 1780557 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2668. Min Range: -3.2668
Max Act: 3.0464. Min Act: -0.1700
Data Index: 3465278 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2668. Min Range: -3.2668
Max Act: 3.0464. Min Act: -0.1700
Data Index: 7044406 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2668. Min Range: -3.2668
Max Act: 3.0148. Min Act: -0.1700
Data Index: 2613475 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2668. Min Range: -3.2668
Max Act: 2.9990. Min Act: -0.1700
Data Index: 3191306 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2668. Min Range: -3.2668
Max Act: 2.9990. Min Act: -0.1700
Data Index: 1288435 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2668. Min Range: -3.2668
Max Act: 2.9990. Min Act: -0.1700
Data Index: 6452777 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2668. Min Range: -3.2668
Max Act: 2.9674. Min Act: -0.1700
Data Index: 5173831 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2668. Min Range: -3.2668
Max Act: 2.9674. Min Act: -0.1700
Data Index: 2727581 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2668. Min Range: -3.2668
Max Act: 2.9674. Min Act: -0.1700
Data Index: 8564315 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2668. Min Range: -3.2668
Max Act: 2.9832. Min Act: -0.1700
Data Index: 8497833 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2668. Min Range: -3.2668
Max Act: 2.9515. Min Act: -0.1700
Data Index: 3795872 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2668. Min Range: -3.2668
Max Act: 2.9515. Min Act: -0.1700
Data Index: 436192 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2668. Min Range: -3.2668
Max Act: 2.9515. Min Act: -0.1700
Data Index: 4690768 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2668. Min Range: -3.2668
Max Act: 2.9357. Min Act: -0.1700
Data Index: 1766157 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2668. Min Range: -3.2668
Max Act: 2.9357. Min Act: -0.1700
Data Index: 1908291 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #19