Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4567 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6580. Min Range: -3.6580
Max Act: 3.6580. Min Act: -0.1700
Data Index: 3786276 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6580. Min Range: -3.6580
Max Act: 3.5797. Min Act: -0.1700
Data Index: 3631292 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6580. Min Range: -3.6580
Max Act: 3.5641. Min Act: -0.1700
Data Index: 3631296 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6580. Min Range: -3.6580
Max Act: 3.5641. Min Act: -0.1700
Data Index: 1472725 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6580. Min Range: -3.6580
Max Act: 3.5328. Min Act: -0.1700
Data Index: 4319577 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6580. Min Range: -3.6580
Max Act: 3.5328. Min Act: -0.1700
Data Index: 2478884 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6580. Min Range: -3.6580
Max Act: 3.4858. Min Act: -0.1700
Data Index: 3631293 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6580. Min Range: -3.6580
Max Act: 3.4858. Min Act: -0.1700
Data Index: 6924410 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6580. Min Range: -3.6580
Max Act: 3.4858. Min Act: -0.1700
Data Index: 6206394 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6580. Min Range: -3.6580
Max Act: 3.4701. Min Act: -0.1700
Data Index: 5524964 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6580. Min Range: -3.6580
Max Act: 3.4544. Min Act: -0.1700
Data Index: 3487973 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6580. Min Range: -3.6580
Max Act: 3.4701. Min Act: -0.1700
Data Index: 3742542 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6580. Min Range: -3.6580
Max Act: 3.4701. Min Act: -0.1700
Data Index: 2056474 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6580. Min Range: -3.6580
Max Act: 3.4388. Min Act: -0.1700
Data Index: 1610073 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6580. Min Range: -3.6580
Max Act: 3.4544. Min Act: -0.1700
Data Index: 6661466 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6580. Min Range: -3.6580
Max Act: 3.4388. Min Act: -0.1700
Data Index: 8323944 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6580. Min Range: -3.6580
Max Act: 3.4388. Min Act: -0.1700
Data Index: 279398 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6580. Min Range: -3.6580
Max Act: 3.4388. Min Act: -0.1700
Data Index: 3901514 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6580. Min Range: -3.6580
Max Act: 3.4231. Min Act: -0.1700
Data Index: 4384691 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6580. Min Range: -3.6580
Max Act: 3.4388. Min Act: -0.1700
Data Index: 5060245 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #19