Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3042 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2292. Min Range: -5.2292
Max Act: 5.1980. Min Act: -0.1700
Data Index: 1727198 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2292. Min Range: -5.2292
Max Act: 5.2292. Min Act: -0.1700
Data Index: 1209659 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2292. Min Range: -5.2292
Max Act: 5.1980. Min Act: -0.1700
Data Index: 3262349 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2292. Min Range: -5.2292
Max Act: 5.1042. Min Act: -0.1700
Data Index: 3962793 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2292. Min Range: -5.2292
Max Act: 5.1042. Min Act: -0.1700
Data Index: 1317613 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2292. Min Range: -5.2292
Max Act: 5.0730. Min Act: -0.1700
Data Index: 2848300 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2292. Min Range: -5.2292
Max Act: 5.0105. Min Act: -0.1700
Data Index: 5431671 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2292. Min Range: -5.2292
Max Act: 4.9792. Min Act: -0.1700
Data Index: 6567140 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2292. Min Range: -5.2292
Max Act: 4.9480. Min Act: -0.1700
Data Index: 5654639 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2292. Min Range: -5.2292
Max Act: 4.9480. Min Act: -0.1700
Data Index: 5170314 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2292. Min Range: -5.2292
Max Act: 4.9167. Min Act: -0.1700
Data Index: 4826625 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2292. Min Range: -5.2292
Max Act: 4.9480. Min Act: -0.1700
Data Index: 4350408 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2292. Min Range: -5.2292
Max Act: 4.9167. Min Act: -0.1700
Data Index: 3631563 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2292. Min Range: -5.2292
Max Act: 4.9167. Min Act: -0.1700
Data Index: 5349859 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2292. Min Range: -5.2292
Max Act: 4.9167. Min Act: -0.1700
Data Index: 3363264 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2292. Min Range: -5.2292
Max Act: 4.8855. Min Act: -0.1700
Data Index: 3167976 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2292. Min Range: -5.2292
Max Act: 4.8855. Min Act: -0.1700
Data Index: 3767947 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2292. Min Range: -5.2292
Max Act: 4.8855. Min Act: -0.1700
Data Index: 1333807 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2292. Min Range: -5.2292
Max Act: 4.8542. Min Act: -0.1700
Data Index: 7825592 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2292. Min Range: -5.2292
Max Act: 4.8542. Min Act: -0.1700
Data Index: 3628138 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19