Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4770 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2222. Min Range: -7.2222
Max Act: 7.2222. Min Act: -0.1700
Data Index: 6687396 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2222. Min Range: -7.2222
Max Act: 7.0972. Min Act: -0.1700
Data Index: 6122494 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2222. Min Range: -7.2222
Max Act: 7.0347. Min Act: -0.1700
Data Index: 7349579 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2222. Min Range: -7.2222
Max Act: 6.9722. Min Act: -0.1700
Data Index: 1910534 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2222. Min Range: -7.2222
Max Act: 6.9722. Min Act: -0.1700
Data Index: 1562483 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2222. Min Range: -7.2222
Max Act: 6.8472. Min Act: -0.1700
Data Index: 4213689 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2222. Min Range: -7.2222
Max Act: 6.7847. Min Act: -0.1700
Data Index: 4503732 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2222. Min Range: -7.2222
Max Act: 6.7535. Min Act: -0.1700
Data Index: 5696935 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2222. Min Range: -7.2222
Max Act: 6.7535. Min Act: -0.1700
Data Index: 3255018 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2222. Min Range: -7.2222
Max Act: 6.7535. Min Act: -0.1700
Data Index: 6102150 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2222. Min Range: -7.2222
Max Act: 6.7535. Min Act: -0.1700
Data Index: 2820214 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2222. Min Range: -7.2222
Max Act: 6.6910. Min Act: -0.1700
Data Index: 5614046 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2222. Min Range: -7.2222
Max Act: 6.6597. Min Act: -0.1700
Data Index: 4840570 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2222. Min Range: -7.2222
Max Act: 6.6597. Min Act: -0.1700
Data Index: 1733293 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2222. Min Range: -7.2222
Max Act: 6.6597. Min Act: -0.1700
Data Index: 8521958 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2222. Min Range: -7.2222
Max Act: 6.5972. Min Act: -0.1700
Data Index: 949497 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2222. Min Range: -7.2222
Max Act: 6.6285. Min Act: -0.1700
Data Index: 3622424 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2222. Min Range: -7.2222
Max Act: 6.5660. Min Act: -0.1700
Data Index: 6571190 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2222. Min Range: -7.2222
Max Act: 6.5972. Min Act: -0.1700
Data Index: 6316961 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2222. Min Range: -7.2222
Max Act: 6.5660. Min Act: -0.1700
Data Index: 58273 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19