Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1124 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6297. Min Range: -5.6297
Max Act: 5.6297. Min Act: -0.1700
Data Index: 4811176 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6297. Min Range: -5.6297
Max Act: 5.6297. Min Act: -0.1700
Data Index: 858391 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6297. Min Range: -5.6297
Max Act: 5.5985. Min Act: -0.1700
Data Index: 254371 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6297. Min Range: -5.6297
Max Act: 5.5047. Min Act: -0.1700
Data Index: 4811175 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6297. Min Range: -5.6297
Max Act: 5.4422. Min Act: -0.1700
Data Index: 4811181 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6297. Min Range: -5.6297
Max Act: 5.4422. Min Act: -0.1700
Data Index: 7185323 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6297. Min Range: -5.6297
Max Act: 5.3172. Min Act: -0.1700
Data Index: 5930229 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6297. Min Range: -5.6297
Max Act: 5.3172. Min Act: -0.1700
Data Index: 739642 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6297. Min Range: -5.6297
Max Act: 5.3172. Min Act: -0.1700
Data Index: 761532 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6297. Min Range: -5.6297
Max Act: 5.3172. Min Act: -0.1700
Data Index: 5572018 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6297. Min Range: -5.6297
Max Act: 5.2860. Min Act: -0.1700
Data Index: 2175280 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6297. Min Range: -5.6297
Max Act: 5.2235. Min Act: -0.1699
Data Index: 652716 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6297. Min Range: -5.6297
Max Act: 5.2547. Min Act: -0.1700
Data Index: 254370 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6297. Min Range: -5.6297
Max Act: 5.2547. Min Act: -0.1700
Data Index: 575816 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6297. Min Range: -5.6297
Max Act: 5.1922. Min Act: -0.1700
Data Index: 1254963 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6297. Min Range: -5.6297
Max Act: 5.2235. Min Act: -0.1700
Data Index: 5283548 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6297. Min Range: -5.6297
Max Act: 5.1922. Min Act: -0.1700
Data Index: 1240028 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6297. Min Range: -5.6297
Max Act: 5.1610. Min Act: -0.1700
Data Index: 5572020 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6297. Min Range: -5.6297
Max Act: 5.1297. Min Act: -0.1700
Data Index: 2660077 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6297. Min Range: -5.6297
Max Act: 5.1297. Min Act: -0.1700
Data Index: 6906384 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19