Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3615 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5922. Min Range: -3.5922
Max Act: 3.5922. Min Act: -0.1700
Data Index: 6160875 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5922. Min Range: -3.5922
Max Act: 3.5922. Min Act: -0.1700
Data Index: 7599365 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5922. Min Range: -3.5922
Max Act: 3.5609. Min Act: -0.1700
Data Index: 6923805 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5922. Min Range: -3.5922
Max Act: 3.5296. Min Act: -0.1700
Data Index: 6004367 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5922. Min Range: -3.5922
Max Act: 3.5609. Min Act: -0.1700
Data Index: 5353824 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5922. Min Range: -3.5922
Max Act: 3.5296. Min Act: -0.1700
Data Index: 79951 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5922. Min Range: -3.5922
Max Act: 3.5296. Min Act: -0.1700
Data Index: 4983185 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5922. Min Range: -3.5922
Max Act: 3.5296. Min Act: -0.1700
Data Index: 7430886 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5922. Min Range: -3.5922
Max Act: 3.4669. Min Act: -0.1700
Data Index: 82289 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5922. Min Range: -3.5922
Max Act: 3.4356. Min Act: -0.1700
Data Index: 21799 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5922. Min Range: -3.5922
Max Act: 3.4356. Min Act: -0.1700
Data Index: 3246877 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5922. Min Range: -3.5922
Max Act: 3.4356. Min Act: -0.1700
Data Index: 3041282 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5922. Min Range: -3.5922
Max Act: 3.4356. Min Act: -0.1700
Data Index: 6813841 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5922. Min Range: -3.5922
Max Act: 3.4356. Min Act: -0.1700
Data Index: 6233688 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5922. Min Range: -3.5922
Max Act: 3.4042. Min Act: -0.1700
Data Index: 697181 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5922. Min Range: -3.5922
Max Act: 3.4042. Min Act: -0.1700
Data Index: 4435346 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5922. Min Range: -3.5922
Max Act: 3.4042. Min Act: -0.1700
Data Index: 194098 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5922. Min Range: -3.5922
Max Act: 3.3729. Min Act: -0.1700
Data Index: 6391505 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5922. Min Range: -3.5922
Max Act: 3.3729. Min Act: -0.1700
Data Index: 3625328 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5922. Min Range: -3.5922
Max Act: 3.3729. Min Act: -0.1700
Data Index: 1927081 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #19