Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 37 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8550. Min Range: -6.8550
Max Act: 6.8550. Min Act: -0.1700
Data Index: 1087221 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8550. Min Range: -6.8550
Max Act: 6.6675. Min Act: -0.1700
Data Index: 297919 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8550. Min Range: -6.8550
Max Act: 6.4175. Min Act: -0.1700
Data Index: 882391 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8550. Min Range: -6.8550
Max Act: 6.3237. Min Act: -0.1700
Data Index: 2574223 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8550. Min Range: -6.8550
Max Act: 6.3862. Min Act: -0.1700
Data Index: 7584700 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8550. Min Range: -6.8550
Max Act: 6.2612. Min Act: -0.1700
Data Index: 3201176 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8550. Min Range: -6.8550
Max Act: 6.2612. Min Act: -0.1700
Data Index: 7008034 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8550. Min Range: -6.8550
Max Act: 6.2300. Min Act: -0.1700
Data Index: 6010026 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8550. Min Range: -6.8550
Max Act: 6.2300. Min Act: -0.1700
Data Index: 1393544 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8550. Min Range: -6.8550
Max Act: 6.1675. Min Act: -0.1700
Data Index: 2815089 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8550. Min Range: -6.8550
Max Act: 6.1987. Min Act: -0.1700
Data Index: 8498844 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8550. Min Range: -6.8550
Max Act: 6.1050. Min Act: -0.1700
Data Index: 6570227 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8550. Min Range: -6.8550
Max Act: 6.1050. Min Act: -0.1700
Data Index: 7146212 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8550. Min Range: -6.8550
Max Act: 6.1362. Min Act: -0.1700
Data Index: 6832348 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8550. Min Range: -6.8550
Max Act: 6.1362. Min Act: -0.1700
Data Index: 5807009 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8550. Min Range: -6.8550
Max Act: 6.1675. Min Act: -0.1700
Data Index: 1434048 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8550. Min Range: -6.8550
Max Act: 6.0737. Min Act: -0.1700
Data Index: 1472702 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8550. Min Range: -6.8550
Max Act: 6.0737. Min Act: -0.1700
Data Index: 4463205 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8550. Min Range: -6.8550
Max Act: 6.0737. Min Act: -0.1700
Data Index: 2257968 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8550. Min Range: -6.8550
Max Act: 6.1050. Min Act: -0.1700
Data Index: 564697 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #19