Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 787 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2350. Min Range: -4.2350
Max Act: 4.2350. Min Act: -0.1700
Data Index: 5875815 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2350. Min Range: -4.2350
Max Act: 4.0475. Min Act: -0.1700
Data Index: 5875816 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2350. Min Range: -4.2350
Max Act: 4.1100. Min Act: -0.1700
Data Index: 8639994 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2350. Min Range: -4.2350
Max Act: 4.0162. Min Act: -0.1700
Data Index: 8639995 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2350. Min Range: -4.2350
Max Act: 3.9850. Min Act: -0.1700
Data Index: 8640002 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2350. Min Range: -4.2350
Max Act: 4.0162. Min Act: -0.1700
Data Index: 8640001 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2350. Min Range: -4.2350
Max Act: 3.9850. Min Act: -0.1700
Data Index: 8639993 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2350. Min Range: -4.2350
Max Act: 3.8287. Min Act: -0.1700
Data Index: 5875813 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2350. Min Range: -4.2350
Max Act: 3.8287. Min Act: -0.1700
Data Index: 8639996 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2350. Min Range: -4.2350
Max Act: 3.8287. Min Act: -0.1700
Data Index: 8639988 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2350. Min Range: -4.2350
Max Act: 3.7974. Min Act: -0.1700
Data Index: 5875811 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2350. Min Range: -4.2350
Max Act: 3.8287. Min Act: -0.1700
Data Index: 8476115 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2350. Min Range: -4.2350
Max Act: 3.7348. Min Act: -0.1700
Data Index: 8639978 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2350. Min Range: -4.2350
Max Act: 3.7974. Min Act: -0.1700
Data Index: 8639973 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2350. Min Range: -4.2350
Max Act: 3.7661. Min Act: -0.1700
Data Index: 8639975 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2350. Min Range: -4.2350
Max Act: 3.8287. Min Act: -0.1700
Data Index: 8639989 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2350. Min Range: -4.2350
Max Act: 3.7661. Min Act: -0.1700
Data Index: 5875806 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2350. Min Range: -4.2350
Max Act: 3.7348. Min Act: -0.1700
Data Index: 8639980 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2350. Min Range: -4.2350
Max Act: 3.6410. Min Act: -0.1700
Data Index: 2904932 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2350. Min Range: -4.2350
Max Act: 3.6723. Min Act: -0.1700
Data Index: 5647749 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19