Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5844 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8159. Min Range: -6.8159
Max Act: 6.8159. Min Act: -0.1700
Data Index: 8672251 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8159. Min Range: -6.8159
Max Act: 6.7847. Min Act: -0.1700
Data Index: 1220808 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8159. Min Range: -6.8159
Max Act: 6.6909. Min Act: -0.1700
Data Index: 6577206 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8159. Min Range: -6.8159
Max Act: 6.5347. Min Act: -0.1700
Data Index: 645793 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8159. Min Range: -6.8159
Max Act: 6.5034. Min Act: -0.1700
Data Index: 77363 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8159. Min Range: -6.8159
Max Act: 6.4722. Min Act: -0.1700
Data Index: 1337754 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8159. Min Range: -6.8159
Max Act: 6.5034. Min Act: -0.1700
Data Index: 5415233 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8159. Min Range: -6.8159
Max Act: 6.5347. Min Act: -0.1700
Data Index: 6963241 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8159. Min Range: -6.8159
Max Act: 6.4409. Min Act: -0.1700
Data Index: 6201451 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8159. Min Range: -6.8159
Max Act: 6.4722. Min Act: -0.1700
Data Index: 4448296 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8159. Min Range: -6.8159
Max Act: 6.4409. Min Act: -0.1700
Data Index: 8174622 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8159. Min Range: -6.8159
Max Act: 6.4097. Min Act: -0.1700
Data Index: 1738322 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8159. Min Range: -6.8159
Max Act: 6.4097. Min Act: -0.1700
Data Index: 2729980 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8159. Min Range: -6.8159
Max Act: 6.4097. Min Act: -0.1700
Data Index: 1003532 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8159. Min Range: -6.8159
Max Act: 6.3784. Min Act: -0.1700
Data Index: 7970470 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8159. Min Range: -6.8159
Max Act: 6.3784. Min Act: -0.1700
Data Index: 7700373 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8159. Min Range: -6.8159
Max Act: 6.3784. Min Act: -0.1700
Data Index: 151538 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8159. Min Range: -6.8159
Max Act: 6.3472. Min Act: -0.1700
Data Index: 3666124 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8159. Min Range: -6.8159
Max Act: 6.3472. Min Act: -0.1700
Data Index: 7200642 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8159. Min Range: -6.8159
Max Act: 6.3159. Min Act: -0.1700
Data Index: 3213988 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19