Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3107 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9296. Min Range: -4.9296
Max Act: 4.9296. Min Act: -0.1700
Data Index: 528507 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9296. Min Range: -4.9296
Max Act: 4.7108. Min Act: -0.1700
Data Index: 1371780 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9296. Min Range: -4.9296
Max Act: 4.6483. Min Act: -0.1700
Data Index: 2872133 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9296. Min Range: -4.9296
Max Act: 4.5546. Min Act: -0.1700
Data Index: 7420815 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9296. Min Range: -4.9296
Max Act: 4.5233. Min Act: -0.1700
Data Index: 8213713 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9296. Min Range: -4.9296
Max Act: 4.5233. Min Act: -0.1700
Data Index: 4338685 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9296. Min Range: -4.9296
Max Act: 4.4921. Min Act: -0.1700
Data Index: 6178004 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9296. Min Range: -4.9296
Max Act: 4.4296. Min Act: -0.1700
Data Index: 7127422 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9296. Min Range: -4.9296
Max Act: 4.4296. Min Act: -0.1700
Data Index: 1129905 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9296. Min Range: -4.9296
Max Act: 4.4296. Min Act: -0.1700
Data Index: 6434272 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9296. Min Range: -4.9296
Max Act: 4.3983. Min Act: -0.1700
Data Index: 7727019 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9296. Min Range: -4.9296
Max Act: 4.3983. Min Act: -0.1700
Data Index: 712532 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9296. Min Range: -4.9296
Max Act: 4.3671. Min Act: -0.1700
Data Index: 8226025 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9296. Min Range: -4.9296
Max Act: 4.3671. Min Act: -0.1700
Data Index: 6537194 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9296. Min Range: -4.9296
Max Act: 4.3671. Min Act: -0.1700
Data Index: 763242 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9296. Min Range: -4.9296
Max Act: 4.3358. Min Act: -0.1700
Data Index: 6105888 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9296. Min Range: -4.9296
Max Act: 4.3671. Min Act: -0.1700
Data Index: 2372528 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9296. Min Range: -4.9296
Max Act: 4.2733. Min Act: -0.1700
Data Index: 909150 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9296. Min Range: -4.9296
Max Act: 4.3046. Min Act: -0.1700
Data Index: 3621331 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9296. Min Range: -4.9296
Max Act: 4.3046. Min Act: -0.1700
Data Index: 8226020 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19