Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1899 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6551. Min Range: -6.6551
Max Act: 6.6551. Min Act: -0.1700
Data Index: 5428371 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6551. Min Range: -6.6551
Max Act: 6.4364. Min Act: -0.1700
Data Index: 6411306 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6551. Min Range: -6.6551
Max Act: 6.4676. Min Act: -0.1700
Data Index: 7331536 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6551. Min Range: -6.6551
Max Act: 6.4364. Min Act: -0.1700
Data Index: 3504511 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6551. Min Range: -6.6551
Max Act: 6.4051. Min Act: -0.1700
Data Index: 5242451 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6551. Min Range: -6.6551
Max Act: 6.3739. Min Act: -0.1700
Data Index: 8217992 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6551. Min Range: -6.6551
Max Act: 6.3739. Min Act: -0.1700
Data Index: 3272477 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6551. Min Range: -6.6551
Max Act: 6.3739. Min Act: -0.1700
Data Index: 983945 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6551. Min Range: -6.6551
Max Act: 6.3426. Min Act: -0.1700
Data Index: 3704608 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6551. Min Range: -6.6551
Max Act: 6.3114. Min Act: -0.1700
Data Index: 3015586 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6551. Min Range: -6.6551
Max Act: 6.3114. Min Act: -0.1700
Data Index: 4053590 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6551. Min Range: -6.6551
Max Act: 6.2801. Min Act: -0.1700
Data Index: 4714083 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6551. Min Range: -6.6551
Max Act: 6.2801. Min Act: -0.1700
Data Index: 8812555 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6551. Min Range: -6.6551
Max Act: 6.2801. Min Act: -0.1700
Data Index: 1671904 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6551. Min Range: -6.6551
Max Act: 6.2489. Min Act: -0.1700
Data Index: 7820002 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6551. Min Range: -6.6551
Max Act: 6.1864. Min Act: -0.1700
Data Index: 8272581 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6551. Min Range: -6.6551
Max Act: 6.1864. Min Act: -0.1700
Data Index: 659845 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6551. Min Range: -6.6551
Max Act: 6.1864. Min Act: -0.1700
Data Index: 2109496 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6551. Min Range: -6.6551
Max Act: 6.1864. Min Act: -0.1700
Data Index: 1308260 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6551. Min Range: -6.6551
Max Act: 6.2176. Min Act: -0.1700
Data Index: 3588598 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19