Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1856 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9364. Min Range: -5.9364
Max Act: 5.9364. Min Act: -0.1700
Data Index: 8605186 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9364. Min Range: -5.9364
Max Act: 5.9051. Min Act: -0.1700
Data Index: 6387494 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9364. Min Range: -5.9364
Max Act: 5.8426. Min Act: -0.1700
Data Index: 6075718 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9364. Min Range: -5.9364
Max Act: 5.8114. Min Act: -0.1700
Data Index: 1209337 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9364. Min Range: -5.9364
Max Act: 5.7801. Min Act: -0.1700
Data Index: 5321142 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9364. Min Range: -5.9364
Max Act: 5.7176. Min Act: -0.1700
Data Index: 5506811 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9364. Min Range: -5.9364
Max Act: 5.7489. Min Act: -0.1700
Data Index: 5141994 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9364. Min Range: -5.9364
Max Act: 5.7176. Min Act: -0.1700
Data Index: 1954236 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9364. Min Range: -5.9364
Max Act: 5.6864. Min Act: -0.1700
Data Index: 1628103 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9364. Min Range: -5.9364
Max Act: 5.6551. Min Act: -0.1700
Data Index: 1940167 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9364. Min Range: -5.9364
Max Act: 5.6551. Min Act: -0.1700
Data Index: 5633302 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9364. Min Range: -5.9364
Max Act: 5.6551. Min Act: -0.1700
Data Index: 3696121 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9364. Min Range: -5.9364
Max Act: 5.6551. Min Act: -0.1700
Data Index: 1763695 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9364. Min Range: -5.9364
Max Act: 5.6239. Min Act: -0.1700
Data Index: 1322502 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9364. Min Range: -5.9364
Max Act: 5.5926. Min Act: -0.1700
Data Index: 3874284 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9364. Min Range: -5.9364
Max Act: 5.5614. Min Act: -0.1700
Data Index: 5526295 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9364. Min Range: -5.9364
Max Act: 5.5301. Min Act: -0.1700
Data Index: 4727587 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9364. Min Range: -5.9364
Max Act: 5.5614. Min Act: -0.1700
Data Index: 8555196 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9364. Min Range: -5.9364
Max Act: 5.5614. Min Act: -0.1700
Data Index: 6804506 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9364. Min Range: -5.9364
Max Act: 5.5614. Min Act: -0.1700
Data Index: 4899646 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #19