Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 368 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5856. Min Range: -8.5856
Max Act: 8.5856. Min Act: -0.1700
Data Index: 1276063 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5856. Min Range: -8.5856
Max Act: 7.9293. Min Act: -0.1700
Data Index: 488255 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5856. Min Range: -8.5856
Max Act: 7.8043. Min Act: -0.1700
Data Index: 3600277 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5856. Min Range: -8.5856
Max Act: 7.7418. Min Act: -0.1700
Data Index: 7619331 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5856. Min Range: -8.5856
Max Act: 7.7418. Min Act: -0.1700
Data Index: 2557856 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5856. Min Range: -8.5856
Max Act: 7.7418. Min Act: -0.1700
Data Index: 4932563 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5856. Min Range: -8.5856
Max Act: 7.6793. Min Act: -0.1700
Data Index: 8782054 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5856. Min Range: -8.5856
Max Act: 7.6793. Min Act: -0.1700
Data Index: 2274618 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5856. Min Range: -8.5856
Max Act: 7.6168. Min Act: -0.1700
Data Index: 4397623 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5856. Min Range: -8.5856
Max Act: 7.5856. Min Act: -0.1700
Data Index: 7904915 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5856. Min Range: -8.5856
Max Act: 7.5231. Min Act: -0.1700
Data Index: 2882376 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5856. Min Range: -8.5856
Max Act: 7.5231. Min Act: -0.1700
Data Index: 2314856 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5856. Min Range: -8.5856
Max Act: 7.4918. Min Act: -0.1700
Data Index: 8145015 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5856. Min Range: -8.5856
Max Act: 7.4918. Min Act: -0.1700
Data Index: 14743 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5856. Min Range: -8.5856
Max Act: 7.4606. Min Act: -0.1700
Data Index: 4429416 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5856. Min Range: -8.5856
Max Act: 7.4606. Min Act: -0.1700
Data Index: 6299837 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5856. Min Range: -8.5856
Max Act: 7.4606. Min Act: -0.1700
Data Index: 2088886 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5856. Min Range: -8.5856
Max Act: 7.4918. Min Act: -0.1700
Data Index: 902554 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5856. Min Range: -8.5856
Max Act: 7.4293. Min Act: -0.1700
Data Index: 5384306 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5856. Min Range: -8.5856
Max Act: 7.3356. Min Act: -0.1700
Data Index: 764940 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #19