Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1863 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4110. Min Range: -6.4110
Max Act: 6.4110. Min Act: -0.1700
Data Index: 968154 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4110. Min Range: -6.4110
Max Act: 6.3485. Min Act: -0.1700
Data Index: 955458 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4110. Min Range: -6.4110
Max Act: 6.3172. Min Act: -0.1700
Data Index: 8773991 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4110. Min Range: -6.4110
Max Act: 6.3172. Min Act: -0.1700
Data Index: 4725779 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4110. Min Range: -6.4110
Max Act: 6.2860. Min Act: -0.1700
Data Index: 4195159 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4110. Min Range: -6.4110
Max Act: 6.2860. Min Act: -0.1700
Data Index: 8310777 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4110. Min Range: -6.4110
Max Act: 6.2235. Min Act: -0.1700
Data Index: 3676860 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4110. Min Range: -6.4110
Max Act: 6.2235. Min Act: -0.1700
Data Index: 2178017 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4110. Min Range: -6.4110
Max Act: 6.1922. Min Act: -0.1700
Data Index: 8483256 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4110. Min Range: -6.4110
Max Act: 6.1610. Min Act: -0.1700
Data Index: 8082935 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4110. Min Range: -6.4110
Max Act: 6.1297. Min Act: -0.1700
Data Index: 5256002 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4110. Min Range: -6.4110
Max Act: 6.1297. Min Act: -0.1700
Data Index: 1435053 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4110. Min Range: -6.4110
Max Act: 6.1297. Min Act: -0.1700
Data Index: 6247521 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4110. Min Range: -6.4110
Max Act: 6.1297. Min Act: -0.1700
Data Index: 1160834 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4110. Min Range: -6.4110
Max Act: 6.1297. Min Act: -0.1700
Data Index: 5838268 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4110. Min Range: -6.4110
Max Act: 6.1610. Min Act: -0.1700
Data Index: 6676568 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4110. Min Range: -6.4110
Max Act: 6.0985. Min Act: -0.1700
Data Index: 6439852 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4110. Min Range: -6.4110
Max Act: 6.0985. Min Act: -0.1700
Data Index: 4657265 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4110. Min Range: -6.4110
Max Act: 6.0985. Min Act: -0.1700
Data Index: 3535377 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4110. Min Range: -6.4110
Max Act: 6.0360. Min Act: -0.1700
Data Index: 5869532 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19