Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4818 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5650. Min Range: -7.5650
Max Act: 7.5650. Min Act: -0.1700
Data Index: 5442933 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5650. Min Range: -7.5650
Max Act: 7.4088. Min Act: -0.1700
Data Index: 5774054 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5650. Min Range: -7.5650
Max Act: 7.4400. Min Act: -0.1700
Data Index: 8145520 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5650. Min Range: -7.5650
Max Act: 7.2838. Min Act: -0.1700
Data Index: 3589421 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5650. Min Range: -7.5650
Max Act: 7.0650. Min Act: -0.1700
Data Index: 3106610 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5650. Min Range: -7.5650
Max Act: 7.0650. Min Act: -0.1700
Data Index: 8528218 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5650. Min Range: -7.5650
Max Act: 7.0338. Min Act: -0.1700
Data Index: 6843472 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5650. Min Range: -7.5650
Max Act: 7.0025. Min Act: -0.1700
Data Index: 4781433 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5650. Min Range: -7.5650
Max Act: 6.9713. Min Act: -0.1700
Data Index: 2605413 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5650. Min Range: -7.5650
Max Act: 6.8775. Min Act: -0.1700
Data Index: 1399969 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5650. Min Range: -7.5650
Max Act: 6.8150. Min Act: -0.1700
Data Index: 6768677 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5650. Min Range: -7.5650
Max Act: 6.8150. Min Act: -0.1700
Data Index: 5038273 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5650. Min Range: -7.5650
Max Act: 6.7838. Min Act: -0.1700
Data Index: 7255445 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5650. Min Range: -7.5650
Max Act: 6.7838. Min Act: -0.1700
Data Index: 6971932 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5650. Min Range: -7.5650
Max Act: 6.7525. Min Act: -0.1700
Data Index: 6561659 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5650. Min Range: -7.5650
Max Act: 6.7525. Min Act: -0.1700
Data Index: 1752227 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5650. Min Range: -7.5650
Max Act: 6.7525. Min Act: -0.1700
Data Index: 4365240 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5650. Min Range: -7.5650
Max Act: 6.6900. Min Act: -0.1700
Data Index: 1710729 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5650. Min Range: -7.5650
Max Act: 6.7525. Min Act: -0.1700
Data Index: 8503195 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5650. Min Range: -7.5650
Max Act: 6.6900. Min Act: -0.1700
Data Index: 5672352 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19