Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3200 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9024. Min Range: -6.9024
Max Act: 6.9024. Min Act: -0.1700
Data Index: 6298022 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9024. Min Range: -6.9024
Max Act: 6.9024. Min Act: -0.1700
Data Index: 39121 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9024. Min Range: -6.9024
Max Act: 6.8399. Min Act: -0.1700
Data Index: 2863583 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9024. Min Range: -6.9024
Max Act: 6.8399. Min Act: -0.1700
Data Index: 7942296 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9024. Min Range: -6.9024
Max Act: 6.8399. Min Act: -0.1700
Data Index: 5480674 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9024. Min Range: -6.9024
Max Act: 6.8399. Min Act: -0.1700
Data Index: 3266035 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9024. Min Range: -6.9024
Max Act: 6.8086. Min Act: -0.1700
Data Index: 201770 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9024. Min Range: -6.9024
Max Act: 6.7774. Min Act: -0.1700
Data Index: 3232318 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9024. Min Range: -6.9024
Max Act: 6.7774. Min Act: -0.1700
Data Index: 5605294 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9024. Min Range: -6.9024
Max Act: 6.8086. Min Act: -0.1700
Data Index: 207281 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9024. Min Range: -6.9024
Max Act: 6.7774. Min Act: -0.1700
Data Index: 3544582 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9024. Min Range: -6.9024
Max Act: 6.7774. Min Act: -0.1700
Data Index: 1003633 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9024. Min Range: -6.9024
Max Act: 6.7461. Min Act: -0.1700
Data Index: 3497566 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9024. Min Range: -6.9024
Max Act: 6.7461. Min Act: -0.1700
Data Index: 7523559 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9024. Min Range: -6.9024
Max Act: 6.7461. Min Act: -0.1700
Data Index: 4220171 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9024. Min Range: -6.9024
Max Act: 6.7461. Min Act: -0.1700
Data Index: 646638 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9024. Min Range: -6.9024
Max Act: 6.7149. Min Act: -0.1700
Data Index: 3487591 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9024. Min Range: -6.9024
Max Act: 6.7149. Min Act: -0.1700
Data Index: 4103172 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9024. Min Range: -6.9024
Max Act: 6.6836. Min Act: -0.1700
Data Index: 5111194 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9024. Min Range: -6.9024
Max Act: 6.6836. Min Act: -0.1700
Data Index: 7396793 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19