Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3547 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2846. Min Range: -6.2846
Max Act: 6.2846. Min Act: -0.1700
Data Index: 7034730 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2846. Min Range: -6.2846
Max Act: 6.0659. Min Act: -0.1700
Data Index: 903143 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2846. Min Range: -6.2846
Max Act: 6.0659. Min Act: -0.1700
Data Index: 3980171 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2846. Min Range: -6.2846
Max Act: 6.0034. Min Act: -0.1700
Data Index: 3644505 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2846. Min Range: -6.2846
Max Act: 5.9409. Min Act: -0.1700
Data Index: 350520 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2846. Min Range: -6.2846
Max Act: 5.9721. Min Act: -0.1700
Data Index: 4479017 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2846. Min Range: -6.2846
Max Act: 5.9096. Min Act: -0.1700
Data Index: 6917964 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2846. Min Range: -6.2846
Max Act: 5.8159. Min Act: -0.1700
Data Index: 565529 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2846. Min Range: -6.2846
Max Act: 5.7534. Min Act: -0.1700
Data Index: 5911249 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2846. Min Range: -6.2846
Max Act: 5.7534. Min Act: -0.1700
Data Index: 5587408 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2846. Min Range: -6.2846
Max Act: 5.6909. Min Act: -0.1700
Data Index: 5768291 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2846. Min Range: -6.2846
Max Act: 5.6909. Min Act: -0.1700
Data Index: 3136381 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2846. Min Range: -6.2846
Max Act: 5.6596. Min Act: -0.1700
Data Index: 8801435 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2846. Min Range: -6.2846
Max Act: 5.6596. Min Act: -0.1700
Data Index: 7250317 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2846. Min Range: -6.2846
Max Act: 5.6596. Min Act: -0.1700
Data Index: 1104975 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2846. Min Range: -6.2846
Max Act: 5.6284. Min Act: -0.1700
Data Index: 3517767 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2846. Min Range: -6.2846
Max Act: 5.5971. Min Act: -0.1700
Data Index: 2640664 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2846. Min Range: -6.2846
Max Act: 5.6284. Min Act: -0.1700
Data Index: 2059424 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2846. Min Range: -6.2846
Max Act: 5.5971. Min Act: -0.1700
Data Index: 653533 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2846. Min Range: -6.2846
Max Act: 5.5971. Min Act: -0.1700
Data Index: 6068622 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19