Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3538 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9512. Min Range: -5.9512
Max Act: 5.9512. Min Act: -0.1700
Data Index: 583304 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9512. Min Range: -5.9512
Max Act: 5.9512. Min Act: -0.1700
Data Index: 7456867 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9512. Min Range: -5.9512
Max Act: 5.9512. Min Act: -0.1700
Data Index: 2794951 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9512. Min Range: -5.9512
Max Act: 5.8887. Min Act: -0.1700
Data Index: 6146754 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9512. Min Range: -5.9512
Max Act: 5.9199. Min Act: -0.1700
Data Index: 5518163 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9512. Min Range: -5.9512
Max Act: 5.8574. Min Act: -0.1700
Data Index: 2957609 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9512. Min Range: -5.9512
Max Act: 5.8574. Min Act: -0.1700
Data Index: 521641 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9512. Min Range: -5.9512
Max Act: 5.8574. Min Act: -0.1700
Data Index: 486094 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9512. Min Range: -5.9512
Max Act: 5.7637. Min Act: -0.1700
Data Index: 1640252 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9512. Min Range: -5.9512
Max Act: 5.7949. Min Act: -0.1700
Data Index: 8465823 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9512. Min Range: -5.9512
Max Act: 5.7949. Min Act: -0.1700
Data Index: 7981976 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9512. Min Range: -5.9512
Max Act: 5.7949. Min Act: -0.1700
Data Index: 5776173 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9512. Min Range: -5.9512
Max Act: 5.7637. Min Act: -0.1700
Data Index: 2521409 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9512. Min Range: -5.9512
Max Act: 5.7949. Min Act: -0.1700
Data Index: 4980273 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9512. Min Range: -5.9512
Max Act: 5.7012. Min Act: -0.1700
Data Index: 7196750 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9512. Min Range: -5.9512
Max Act: 5.7324. Min Act: -0.1700
Data Index: 1589672 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9512. Min Range: -5.9512
Max Act: 5.7324. Min Act: -0.1700
Data Index: 6500499 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9512. Min Range: -5.9512
Max Act: 5.7012. Min Act: -0.1700
Data Index: 3672247 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9512. Min Range: -5.9512
Max Act: 5.6699. Min Act: -0.1700
Data Index: 209690 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9512. Min Range: -5.9512
Max Act: 5.6699. Min Act: -0.1700
Data Index: 4765652 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19