Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5657 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2846. Min Range: -8.2846
Max Act: 8.2846. Min Act: -0.1700
Data Index: 3304439 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2846. Min Range: -8.2846
Max Act: 8.2846. Min Act: -0.1700
Data Index: 7367067 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2846. Min Range: -8.2846
Max Act: 8.2221. Min Act: -0.1700
Data Index: 8551878 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2846. Min Range: -8.2846
Max Act: 8.2221. Min Act: -0.1700
Data Index: 613548 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2846. Min Range: -8.2846
Max Act: 8.2221. Min Act: -0.1700
Data Index: 4577963 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2846. Min Range: -8.2846
Max Act: 8.1596. Min Act: -0.1700
Data Index: 116064 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2846. Min Range: -8.2846
Max Act: 8.2221. Min Act: -0.1700
Data Index: 6171142 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2846. Min Range: -8.2846
Max Act: 8.1596. Min Act: -0.1700
Data Index: 165693 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2846. Min Range: -8.2846
Max Act: 8.1596. Min Act: -0.1700
Data Index: 165690 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2846. Min Range: -8.2846
Max Act: 8.1596. Min Act: -0.1700
Data Index: 298228 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2846. Min Range: -8.2846
Max Act: 8.2221. Min Act: -0.1700
Data Index: 1737791 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2846. Min Range: -8.2846
Max Act: 8.0971. Min Act: -0.1700
Data Index: 2832684 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2846. Min Range: -8.2846
Max Act: 8.0971. Min Act: -0.1700
Data Index: 8290525 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2846. Min Range: -8.2846
Max Act: 8.0346. Min Act: -0.1700
Data Index: 6665119 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2846. Min Range: -8.2846
Max Act: 8.0971. Min Act: -0.1700
Data Index: 1685457 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2846. Min Range: -8.2846
Max Act: 8.0971. Min Act: -0.1700
Data Index: 2127136 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2846. Min Range: -8.2846
Max Act: 8.0971. Min Act: -0.1700
Data Index: 2819605 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2846. Min Range: -8.2846
Max Act: 8.0971. Min Act: -0.1700
Data Index: 2324560 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2846. Min Range: -8.2846
Max Act: 8.0971. Min Act: -0.1700
Data Index: 591322 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2846. Min Range: -8.2846
Max Act: 8.0346. Min Act: -0.1700
Data Index: 1868022 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #19