Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3532 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1120. Min Range: -8.1120
Max Act: 8.1120. Min Act: -0.1700
Data Index: 5701727 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1120. Min Range: -8.1120
Max Act: 8.1120. Min Act: -0.1700
Data Index: 3460948 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1120. Min Range: -8.1120
Max Act: 8.0495. Min Act: -0.1700
Data Index: 7732316 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1120. Min Range: -8.1120
Max Act: 8.0495. Min Act: -0.1700
Data Index: 7251316 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1120. Min Range: -8.1120
Max Act: 7.9870. Min Act: -0.1700
Data Index: 8541072 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1120. Min Range: -8.1120
Max Act: 7.9245. Min Act: -0.1700
Data Index: 8769926 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1120. Min Range: -8.1120
Max Act: 7.7995. Min Act: -0.1700
Data Index: 3359764 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1120. Min Range: -8.1120
Max Act: 7.7995. Min Act: -0.1700
Data Index: 5686117 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1120. Min Range: -8.1120
Max Act: 7.7995. Min Act: -0.1700
Data Index: 6057823 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1120. Min Range: -8.1120
Max Act: 7.7370. Min Act: -0.1700
Data Index: 2703683 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1120. Min Range: -8.1120
Max Act: 7.7370. Min Act: -0.1700
Data Index: 2421095 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1120. Min Range: -8.1120
Max Act: 7.7370. Min Act: -0.1700
Data Index: 6274836 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1120. Min Range: -8.1120
Max Act: 7.6745. Min Act: -0.1700
Data Index: 7247377 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1120. Min Range: -8.1120
Max Act: 7.6745. Min Act: -0.1700
Data Index: 3845851 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1120. Min Range: -8.1120
Max Act: 7.6745. Min Act: -0.1700
Data Index: 3528020 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1120. Min Range: -8.1120
Max Act: 7.7370. Min Act: -0.1698
Data Index: 547845 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1120. Min Range: -8.1120
Max Act: 7.6120. Min Act: -0.1700
Data Index: 2919147 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1120. Min Range: -8.1120
Max Act: 7.6745. Min Act: -0.1700
Data Index: 4223209 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1120. Min Range: -8.1120
Max Act: 7.6745. Min Act: -0.1700
Data Index: 6073958 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1120. Min Range: -8.1120
Max Act: 7.6745. Min Act: -0.1700
Data Index: 4477294 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19